A method for updating product data of a shipment product and related electronic device

Abstract

Disclosed is a method, performed by an electronic device, for updating product data of a shipment product. The method comprises obtaining historical data associated with the shipment product. The method comprises determining, based on the historical data, one or more shipment product parameters, by applying a forecasting model to the historical data. The method comprises generating, based on the one or more shipment product parameters, a value change parameter indicative of a change of a value associated with the shipment product. The method comprises predicting, based on the historical data and the value change parameter, a selection parameter indicative of a likelihood that a user selects the shipment product based on the value change parameter. The method comprises determining an updated value parameter associated with the shipment product based on one or more of: the historical data, the value change parameter, and the selection parameter.

Description

[0001] A METHOD FOR UPDATING PRODUCT DATA OF A SHIPMENT PRODUCT AND

[0002] RELATED ELECTRONIC DEVICE

[0003] The present disclosure pertains to the field of transport and freight. The present disclosure relates to a method for updating product data of a shipment product associated with a shipment of an item and related electronic device.

[0004] BACKGROUND

[0005] Shipment of items may involve one or more shipment products for a user to select. For example, a user may select a premium shipping container for the shipment of the item, hangers for the item, a rollable, and / or time extensions. However, the availability of the shipment products may vary significantly depending on a broad range of factors.

[0006] SUMMARY

[0007] Control and management of the inventory of shipment products is affected by many factors, such as seasonality and availability.

[0008] Accordingly, there is a need for an electronic device and a method for updating product data of a shipment product associated with a shipment of an item, which mitigate, alleviate, or address the shortcomings existing and may allow for a more accurate, robust, and time-efficient prediction of availability for a shipment product, such as prediction of the product data of a shipment product associated with a shipment.

[0009] Disclosed is a method, performed by an electronic device, for updating product data of a shipment product. The method comprises obtaining historical data associated with the shipment product. The method comprises determining, based on the historical data, one or more shipment product parameters, e.g. by applying a forecasting model to the historical data. The method comprises generating, based on the one or more shipment product parameters, a value change parameter indicative of a change of a value associated with the shipment product. The method comprises predicting, based on the historical data and / or the value change parameter, a selection parameter indicative of a likelihood that a user selects the shipment product based on the value change parameter. The method comprises determining an updated value parameter associated with the shipment product based on one or more of: the historical data, the value change parameter, the one or more shipment product parameters, and the selection parameter. The method may comprise providing, based on the updated value parameter, updated product data associated with the shipment product.

[0010] Disclosed is an electronic device comprising memory circuitry, processor circuitry, and an interface, wherein the electronic device is configured to perform any of the methods according to the methods disclosed herein.

[0011] Disclosed is a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by an electronic device cause the electronic device to perform any of the methods disclosed herein.

[0012] It is an advantage of the present disclosure that the disclosed electronic device and method provide a more accurate, robust, and time-efficient prediction of the product data of a shipment product. This may result in improving the control and management of inventory of the shipment products. For example, the shipment of the items with the shipment product selected by the consignee can be carried out in a timely and efficient manner. For example, it may be beneficial to predict the impact of inventory availability and product cost on a user selection of a shipment product.. The disclosed technique can be applied to any future shipment product and can be extended to include various shipment product parameters.

[0013] BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above and other features and advantages of the present disclosure will become readily apparent to those skilled in the art by the following detailed description of exemplary embodiments thereof with reference to the attached drawings, in which:

[0015] Fig. 1 is a flow-chart illustrating an exemplary method, performed by an electronic device, for updating product data of a shipment product associated with a shipment of an item according to this disclosure, and

[0016] Fig. 2 is a block diagram illustrating an exemplary electronic device according to this disclosure.

[0017] DETAILED DESCRIPTION

[0018] Various exemplary embodiments and details are described hereinafter, with reference to the figures when relevant. It should be noted that the figures may or may not be drawn to scale and that elements of similar structures or functions are represented by like reference numerals throughout the figures. It should also be noted that the figures are only intended to facilitate the description of the embodiments. They are not intended as an exhaustive description of the disclosure or as a limitation on the scope of the disclosure. In addition, an illustrated embodiment needs not have all the aspects or advantages shown. An aspect or an advantage described in conjunction with a particular embodiment is not necessarily limited to that embodiment and can be practiced in any other embodiments even if not so illustrated, or if not so explicitly described.

[0019] The figures are schematic and simplified for clarity, and they merely show details which aid understanding the disclosure, while other details have been left out. Throughout, the same reference numerals are used for identical or corresponding parts.

[0020] A container disclosed herein refers to a housing where items to be shipped are enclosed for transport.

[0021] An item disclosed herein may refer to an object that is to be placed in a container for transport. For example, an item may be seen as an item of cargo, e.g., an item of freight, e.g., an object to be shipped. It is noted that the terms item may be used interchangeably with cargo. For example, an item may comprise commodities that can be placed into containers, such as goods, such as consumer goods of large manufacturing corporations, generic consumer goods as shoes, clothing, toys and fast-moving-consumer-goods as packaged foods, beverages, toiletries, and medicines.

[0022] For example, the items disclosed herein may be seen as commodities that can be packed into e.g., stackable boxes with variable weights and volumes that are transported in one or more containers.

[0023] A shipment may for example be seen as transportation of an item from a first location (e.g., origin) to a second location (e.g., destination). For example, the shipment may be seen as shipment of a container comprising the item. A shipment may involve one or more modality of transportation such as ocean carrier, land carrier, and / or air carrier.

[0024] A shipment product is for example a product associated with a shipment. For example, the shipment product may be a service (such as a Value-Added Service (VAS)) and / or an activity and / or equipment and / or a resource associated with the shipment (e.g. part of an inventory to be used in the shipment). In some examples, the shipment product is an addon (such as an addon product) associated with the shipment. In some examples, the shipment product is associated with a type of container of the shipment, such as one or more of: a dry storage container, a flat rack container, a refrigerated container, a special purpose container, and a premium quality container . For example, the shipment product may include one or more of: a time extension, garments on hanger service, a rollable, premium quality container, consolidation services, etc. A premium quality container may be for example a container of a specific quality, such as a food grade container, a container of a specific age, a container designed for specific commodities like electronics, etc. A rollable may be seen as a shipment product allowing moving a container in upcoming vessel.

[0025] Fig. 1 shows a flow diagram of an exemplary method, performed by an electronic device, e.g. for updating product data of a shipment product associated with a shipment of an item, according to the disclosure. The method 100 is performed by an electronic device, such as the electronic device disclosed herein, such as electronic device 300 of Fig. 2.

[0026] The method 100 comprises obtaining S102 historical data associated with the shipment product. Historical data may be seen as previous (e.g., past) data associated with the shipment product. The historical data can include historical data associated with one or more shipment products. For example, the historical data may include historical data associated with a port. In some examples, the historical data includes transactional data. In some examples, the historical data is obtained per port. In some examples, the historical data with a port may be aggregated (e.g., grouped) based on the port. In some examples, the historical data may be seen as empirical (e.g., observed, detected, measured, etc.) historical data.

[0027] The historical data associated with the shipment product is for example associated with a time period (e.g., a month). For example, obtaining the historical data associated with the shipment product comprises obtaining the historical data associated with a time period (e.g., a month). In some examples, historical data may be seen as monthly historical data (e.g., historical data associated with a month), and / or yearly historical data and / or weekly historical data.

[0028] The historical data for example comprises historical import revenue and / or export revenue per volume (e.g., per container size and / or per container type). In some examples, a container type may be a forty-foot equivalent (FFE) or a twenty-foot equivalent. The historical data for example comprises historical import revenue and / or export revenue per volume for each month.

[0029] The historical data for example comprises historical import revenue and / or historical export revenue and / or historical import or export revenue volume ratio. The historical data for example comprises historical import revenue and / or historical export revenue and / or historical volume ratio for each month and at port level. The historical import revenue may be seen as the historical (e.g., past) revenue associated with the import of an item. The historical export revenue may be seen as the historical (e.g., past) revenue associated with the export of an item. In some examples, the historical import or export revenue volume ratio may be seen as a ratio of import revenue per volume or a ratio of export revenue per volume. For example, when the container is a forty-foot equivalent container the historical volume ratio may be seen as a historical revenue per FFE ratio.

[0030] The historical data for example comprises a historical selection parameter (e.g., adoption percentage) per shipment product (e.g., VAS / addon). For example, the historical selection parameter may be a value (e.g., integer, decimal, percentage, etc.). In some examples, the historical selection parameter may be a parameter indicative of the likelihood that a user selects (e.g., purchases) a shipment product. In some examples, each historical selection parameter is associated with a historical value (e.g., cost) of a shipment product.

[0031] The historical data for example comprises a mean turnaround time and / or a median turnaround time for returning the container for users who bought a time extension and / or a mean turnaround time and / or a median turnaround time for returning the container for users who did not select time extension. In some examples, the turnaround time is the time period between the time that the container arrives at a terminal to be discharged off the vessel and the time that the container returns to the terminal. In some examples, the turnaround time includes the detention time.

[0032] A time extension may for example be seen as an additional period of time (e.g., days, hours) during which a container may be stored at a port and / or retained at the recipient outside the port or terminal. A consignee can select a time extension (such as a free time extension) at the time of booking a shipping of a container to allow more time for loading and / or unloading of the container. This helps a consignee and / or consignor to mitigate the risk of costly operations, such as Demurrage and Detention (D&D) applicable when the consignee holds carrier equipment in the terminal for longer than the agreed amount of time.

[0033] The historical data for example comprises a mean import inventory availability and / or a median import inventory availability and / or a mean export inventory availability and / or a median export availability, e.g. per month. The historical data for example comprises a mean import inventory availability and / or a median import inventory availability and / or a mean export inventory availability and / or a median export availability for each shipment product (e.g. VAS).

[0034] In some examples, the shipment product can be a piece of inventory. For example, the inventory comprises equipment such as physical resources (e.g., premium quality containers, containers with hangers) a shipment product. In some examples, import inventory availability may indicate the number of shipment products (e.g., premium quality containers) arriving at a country (e.g., a port) and available for booking for an upcoming time period. In some examples, the export inventory availability may indicate the number of shipment products (e.g., premium quality containers) departing from a country (e.g., a port) and available for booking for an upcoming period.

[0035] The historical data for example comprises inventory usage, such as inventory consumption. In some examples, inventory usage may indicate the used inventory for a shipment product (e.g., premium quality container). For example, the used inventory may indicate the difference between an initial inventory and a current inventory.

[0036] In some examples, obtaining S102 the historical data comprises receiving and / or retrieving the historical data from a storage medium, such as one or more databases which store historical data. In some examples, obtaining the historical data comprises obtaining the historical data from one or more transactional data sources. In some examples, a transactional data source may be seen as a database comprising data associated with a transaction of a shipment (e.g., a transaction between a consignee and consignor).

[0037] For example, obtaining S102 the historical data comprises receiving and / or retrieving the historical data from a storage medium associated with a port. In some examples, obtaining the historical data comprises obtaining the historical data from a memory of the electronic device (e.g., electronic device 300 of Fig. 2). In some examples, obtaining the historical data comprises obtaining (e.g., receiving) the historical data from one or more external servers.

[0038] The method 100 comprises determining S104, based on the historical data, one or more shipment product parameters, e.g. by applying S104A a forecasting model to the historical data. In other words, the forecasting model takes as input the historical data and output the one or more shipment product parameters. Stated differently, the one or more shipment product parameters may be seen as one or more future shipment product parameters, such as one or more shipment product parameters predicted and / or forecasted for a future period, such as for an upcoming period. In one or more example methods, the one or more shipment product parameters are associated with the shipment product. In some examples, the one or more shipment product parameters are associated with the value and / or volume of the shipment. In one or more example methods, the one or more shipment product parameters comprise one or more shipment product parameters per port and / or per time period (e.g., per month). In some examples, determining S104, based on the historical data, the one or more shipment product parameters comprises determining the one or more shipment product parameters per port and / or per time period. In some examples, the one or more shipment product parameters are outputs of the forecasting model.

[0039] In one or more example methods, the one or more shipment product parameters comprise one or more of: revenue per volume, import revenue per volume, export revenue per volume, import volume, export volume, import and / or export pattern, import and / or export revenue pattern, import and / or export volume pattern, and associated seasonality parameter, and associated variability parameter. In some examples, a shipment product parameter comprise a value (e.g., Boolean, integer, decimal, percentages, etc.). For example, the one or more shipment product parameters comprise one or more of: revenue per volume parameter, import revenue per volume parameter, export revenue per volume parameter, import and / or export pattern parameter, import and / or export revenue pattern parameter, import and / or export volume pattern parameter, a seasonality parameter, and a variability parameter. In some examples, the shipment product parameter (e.g. one or more of: revenue per volume, import revenue per volume, export revenue per volume, import and / or export pattern, import and / or export revenue pattern, and import and / or export volume pattern) can be associated with a seasonality parameter, and / or a variability parameter. In some examples, the historical data associated with the shipment product can be seen as input for the forecasting model. In other words, the method may comprise inputting historical data into the forecasting model. For example, the method comprises determining, based on the historical data, one or more shipment product parameters, by applying a forecasting model to one or more of: a historical import and / or export revenue per volume, a historical import and / or historical export revenue, historical revenue per volume ratio, a historical selection parameter per shipment product, a mean and / or median turnaround time, a mean and / or median import inventory availability and / or export inventory availability, and a mean and / or median inventory consumption for each shipment product.

[0040] In some examples, the revenue per volume may comprise predicted revenue per volume. In some examples, revenue per volume may be seen as indicative of a ratio of the revenue associated with a shipment product over the volume (e.g., dimensions, container size and / or container type) of a container associated with the shipment product. For example, when the container associated with the shipment product is a forty-foot equivalent container, the revenue per volume may be seen as a revenue per FFE ratio. In some examples, the revenue per volume associated with a shipment can be seen as an average of import revenue per volume and export revenue per volume associated with the given shipment. Revenue per volume for example comprises import revenue per month and / or export revenue per month. In some examples, the import revenue per volume may comprise a predicted (e.g., forecasted) import revenue per volume. In some examples, import revenue per volume may be seen as indicative of a ratio of the import revenue associated with a shipment product over the volume (e.g., dimensions, container size and / or container type) of a container associated with the shipment product. In some examples, the export revenue per volume may comprise predicted (e.g., forecasted) export revenue per volume. In some examples, export revenue per volume may be seen as indicative of a ratio of the export revenue associated with a shipment product over the volume (e.g., dimensions, container size and / or container type) of a container associated with the shipment product.

[0041] In some examples, the import and / or export pattern may include the import and / or export volume pattern and / or the import and / or export revenue pattern and / or a pattern for import and / or export revenue per volume. In some examples, the import and / or export pattern may be seen as a pattern indicative of how the import and / or the export varies over time. In some examples, the import and / or export volume pattern may be seen as a pattern indicative of how the import volume and / or the export volume varies over time. . In some examples, the import and / or export revenue pattern may be seen as a pattern indicative of how the import revenue and / or the export revenue varies over time. In other words, the import and / or export pattern can indicate an overall trend of the revenue (e.g., import and / or export revenue), the volume, and / or the revenue per volume.

[0042] The seasonality parameter may be seen as a parameter indicative of seasonality of a shipment product, e.g. based on the historical data associated with the shipment product. Seasonality may be seen as a characteristic showing a pattern over time, such as a periodical pattern over time. In some examples, the seasonality parameter comprises a value (e.g., Boolean, decimal, fraction, integer, etc.) indicative of a characteristic of a time series in which the data experiences periodical and / or predictable changes (e.g., patterns) that may recur over a time period (such as every calendar year). For example, seasonality parameter may be indicative of seasonal patterns associated with a data set (e.g., a time series). For example, each seasonality parameter may be associated with a corresponding time period, such as a corresponding season (e.g. a month or quarter of a year). The seasonality parameter may for example be seen as a value indicative of the seasonal impact (e.g., on the revenue per volume) associated with a given month. The seasonality parameter may be seen as indicative of the seasonality (e.g., of the revenue per volume associated with a shipment product) in a given month.

[0043] The variability parameter may be seen as a parameter characterizing the variability of a shipment product over time. The variability parameter includes for example a value (e.g., Boolean, decimal, fraction, integer, etc.). For example, the variability parameter is indicative of variability of the shipment product parameter over time, e.g. the variability of revenue per volume, import revenue per volume, export revenue per volume, and / or import and / or export volume pattern over time. The variability parameter may be based on the historical data associated with the shipment product. In some examples, the variability parameter may be seen as a value indicative of a spread (e.g., a variance) of historical data (e.g., around the mean). For example, the variability parameter may indicate the accuracy of the output of the forecasting model. In some examples, the variability parameter can be seen as a confidence parameter (e.g., a confidence score) that provides how confident the forecasting model is with the shipment product parameter outputted. In some examples, the variability parameter may be seen as a confidence interval. In some examples, the variability parameter may be seen as indicative of the variability in the import and / or export volume pattern, e.g. for upcoming period, such as upcoming month(s).

[0044] In one or more example methods, the forecasting model comprises a machine-learning based time-series forecasting model. In one or more examples, forecasting model may be configured to carry out one or more forecasting techniques. In one or more examples, the forecasting technique comprises a machine learning based time-series forecasting technique. For example, applying the forecasting technique comprises applying an Autoregressive Integrated Moving Average (ARIMA) model. In some examples, the forecasting technique comprises applying an Autoregressive Integrated Moving Average with Explanatory Variable (ARIMAX) model. In some examples, the forecasting technique comprises applying a Seasonal Auto-Regressive Integrated Moving Average with exogenous factors (SARIMAX) model. In one or more example methods, the forecasting model may be based on a Recurrent Neural Network model.

[0045] In some examples, the forecasting model (e.g., machine learning based techniques (e.g., algorithms)) is configured to predict, based on the historical data, the shipment product parameter (e.g. import revenue per volume (e.g., per FFE)). In some examples, the forecasting model (e.g., machine learning based techniques (e.g., algorithms)) is configured to predict, based on the historical data, the export revenue per volume (e.g., per FFE). In some examples, the forecasting model is configured to predict (e.g., for an upcoming time period, e.g., for upcoming months), based on the historical data, the variability parameter associated with the shipment product parameter (e.g. export revenue per volume and / or the import revenue per volume).

[0046] In some examples, the forecasting model is configured to determine (e.g., predict) one or more shipment product parameters (e.g., import revenue per volume and / or export revenue per volume) associated with a future time period (e.g., 3 months).

[0047] In some examples, the forecasting model (e.g., machine learning based techniques) is configured to predict the import volume (e.g., FFE). In some examples, the forecasting model (e.g., machine learning based techniques) is configured to predict the export volume (e.g., FFE). In some examples, the forecasting model is configured to predict (e.g., for an upcoming time period, e.g., for upcoming months) the variability (e.g., a value) associated with the export volume and / or the import volume. The output of the forecasting model may be used for simulation of the updated value parameter.

[0048] The method 100 comprises generating S106, based on the one or more shipment product parameters, a value change parameter indicative of a change of a value associated with the shipment product. In some examples, the value change parameter indicates a change of the value associated with the shipment product over a time period. In one or more example methods, the value comprises availability and / or cost associated with the shipment product. For example, the value change parameter is indicative of a change (e.g., recommended change) in the availability and / or the cost of the shipment product. The value change parameter is for example parameter that can quantify the change in value (e.g., a percentage of change, such as + / - X %, where X is a real number). For example, the value change parameter is indicative of a change, over a period of time, of a value associated with the shipment product. The value change parameter is for example, indicative of a change (e.g., a recommended change) in value of the shipment product. In some examples, the value change parameter may be seen as a parameter for inventory optimisation and demand driven control of the inventory. In some examples, the value change parameter may be seen as enabling resource control.

[0049] The method 100 comprises predicting S108, based on the historical data and the value change parameter, a selection parameter indicative of a likelihood that a user selects the shipment product based on the value change parameter. In some examples, the selection parameter may be indicative of a change (e.g., a percentage change) in user selection and / or adoption of the shipment product. In some examples, the selection parameter is predicted based the value change parameter and one or more of: : a historical import and / or export revenue per volume, a historical import and / or historical export revenue, historical revenue per volume ratio, a historical selection parameter per shipment product, a mean and / or median turnaround time, a mean and / or median import inventory availability and / or export inventory availability, and a mean and / or median inventory consumption for each shipment product. In some examples, the selection parameter may include a value (e.g., Boolean integer, decimal, percentage, etc.). For example, the historical selection parameter may be indicative of the likelihood that a user selects (e.g., purchases) a shipment product. In some examples, the selection parameter may be associated with the value change parameter. For example, the selection parameter may be 90% when the value change parameter is +0,5%, which means that the user is likely with 90% to select the shipment product when the value of shipment product has changed of +0,5%.

[0050] The user may be seen as a user of the electronic device disclosed herein (such as the electronic device 300 of Fig. 2). In some examples, the user may be seen as a user of one or more shipment products. For example, the user may be a potential selector of a shipment product (e.g. a consignee of a shipment). In some examples, when a user selects a shipment product, the given shipment product may be seen as a selected shipment product. In some examples, a shipment product owner (e.g. a pricing manager) can use the value change parameter and the selection parameter to set the value associated with the shipment product.

[0051] The method 100 comprises determining S110 an updated value parameter associated with the shipment product based on one or more of: the historical data, the value change parameter, the one or more shipment product parameters, and the selection parameter. The updated value parameter may be seen as a parameter indicative of an updated value of a shipment product. For example, the update value parameter can comprise the updated value of the shipment product (e.g. an updated cost of the shipment product).

[0052] The method 100 comprises providing S112, based on the updated value parameter, updated product data associated with the shipment product. In some examples, the updated product data may be seen as updated data of the shipment product. In other words, the updated product data can include the updated value parameter or another value parameter. For example, the updated value parameter can be used to adjust the updated product data or not. In some examples, the provision of the updated product data may be seen as a recommendation (e.g., a cost recommendation). For example, providing updated product data associated with the shipment product comprises providing a recommendation associated with the shipment product (e.g., addons and / or VAS). For example, the updated product data is based on updated value parameter which has taken into account the selection parameter and the shipment product parameters (e.g. the import and / or export volume pattern, associated variability parameter, associated seasonality parameter, and / or corresponding (e.g., corresponding impact on) inventory availability). In some examples, providing updated product data comprises providing updated product data via an electronic device, (e.g., electronic device 300 of Fig .2) For example, providing updated product data comprises providing updated product data via an interface of an electronic device (e.g., via the interface 303 of the electronic device 300 of Fig.2).

[0053] In one or more example methods, the forecasting model comprises a first forecasting model for a first shipment product parameter and / or a second forecasting model for a second shipment product parameter. In some examples, the first shipment product parameter is different from the second shipment parameter. In some examples, the method 100 comprises determining S104, based on the historical data, the first shipment product parameter, by applying S104A the first forecasting model to the historical data.

[0054] In some examples, the first forecasting model may be seen as a forecasting model (e.g., a machine learning based forecasting model) configured to predict the first shipment product parameter, such as import revenue per volume. In one or more examples, the first forecasting model may be configured to carry out one or more forecasting techniques. For example, the first forecasting model comprises a machine learning based time-series forecasting technique. For example, the forecasting technique carried out by the first forecasting model comprises applying an Autoregressive Integrated Moving Average (ARIMA) model. In some examples, the first shipment product parameter may be seen as an output of the first forecasting model. The first shipment product parameter is predicted by the first forecasting model for example based on historical data. In some examples, the first shipment product parameter may be a predicted (e.g., future) import revenue per volume (e.g., per FFE). For example, the first shipment product parameter is associated with a time period (e.g., a month). In one or more examples, the first shipment product parameter comprises a first predicted shipment product parameter indicative of a first shipment product.

[0055] In one or more examples, the one or more shipment product parameters comprise the first shipment product parameter and / or the second shipment product parameter. In some examples, the one or more shipment product parameters comprise one or more predicted shipment product parameters. In some examples, the first shipment product parameter comprises parameter(s) for import, e.g. based on a historical (e.g., past, e.g. a past time period) ratio of import revenue per volume.

[0056] In one or more example methods, the first forecasting model may be configured to determine (such as predict, e.g., based on historical data associated with the shipment product) the first shipment product parameter for one or more months. In some examples, the method 100 comprises determining S104, based on the historical data, the second shipment product parameter, by applying S104A the second forecasting model to the historical data. In some examples, the second forecasting model may be configured to predict the second shipment product parameter based on the historical data. The second shipment product parameter may be related to export, such as export revenue per volume. In one or more examples, the second forecasting model may be configured to carry out one or more forecasting techniques. For example, the second forecasting model comprises a machine learning based time-series forecasting technique. For example, the forecasting technique carried out by the second forecasting model comprises applying an Autoregressive Integrated Moving Average (ARIMA) model. In some examples, the second shipment product parameter may be seen as an output of the second forecasting model. The second shipment product parameter is predicted for example based on historical data. In some examples, the second shipment product parameter may be a predicted (e.g., future) export revenue per volume (e.g., FFE). For example, the second shipment product parameter is associated with a time period (e.g., a month). In one or more examples, the second shipment product parameter comprises a second predicted shipment product parameter indicative of a second shipment product. In some examples, the second shipment product parameter comprises parameter(s) for export, such as based on a historical (e.g., past) export revenue per volume. In one or more example methods, the second forecasting model may be configured to determine (such as predict, e.g., based on historical data associated with the shipment product) the second shipment product parameter for one or more months.

[0057] In some examples, the method comprises generating, based on the variability parameter associated with a shipment product parameter, a confidence interval associated with the shipment product parameter. In some examples, the confidence interval comprises at least two values (e.g., integer, decimal, percentage, etc.). For example, the confidence interval may provide a range of values within which the shipment product parameter may be (e.g., with a certain confidence level (e.g., 95%)).

[0058] In one or more example methods, generating S106 the value change parameter comprises determining S106A a first ratio between at least two shipment product parameters of the one or more shipment product parameters for a first time period. In some examples, the first ratio may be seen a ratio between two determined or predicted shipment product parameters for the first time period. For example, the first ratio can include a ratio between an import revenue per volume (e.g., FFE) predicted by the forecasting model and an export revenue per volume predicted by the forecasting model. For example, the first ratio is associated with the first time period (e.g., a month). The first time period may be seen as a future period, such as an upcoming time period, such as an upcoming month(s). In some examples, the first time period (e.g., month) may be seen as time period (e.g., a future time period, e.g., a future month) used in the forecasting model.

[0059] In one or more example methods, generating S106 the value change parameter comprises determining S106B a second ratio between the at least two shipment product parameter of the one or more shipment product parameters for a second time period. The second ratio is a ratio between two determined or predicted shipment product parameters for the second time period. For example, the two determined or predicted shipment product parameters used to determine the first ratio are also used to determine the second ratio but for a second time period, different that the first time period. In some examples, the second ratio may be a forecast (e.g., predicted) ratio of import revenue per volume over export revenue per volume (e.g., container volume). The second ratio is for example based on one or more predicted shipment product parameters (e.g., import revenue per volume and / or export revenue per volume). For example, the second ratio is associated with a second time period (e.g., a month). The second time period may be seen as a future period, such as an upcoming time period, such as an upcoming month(s) (e.g., a future and / or present time period) different from the first time period. In one or more example methods, the first time period precedes the second time period.

[0060] In one or more example methods, generating S106 the value change parameter comprises determining S106C a ratio difference based on a difference between the first ratio and the second ratio. In some examples, the ratio difference indicates the difference between the second ratio and the first ratio. In some examples, determining the ratio difference comprises calculating (e.g., subtracting) the ratio difference based on the first ratio and the second ratio. In some examples, the ratio difference may indicate the change between the first and second ratio. For example, determining the ratio difference comprises subtracting the first ratio from the second ratio. The ratio difference is for example indicative of a change in at least one of the one or more shipment product parameters (such as import and / or export pattern, such as import and / or export volume pattern) associated with an upcoming month, e.g. a future month. The ratio difference provides for example information about how much the shipment products used for the ratios (e.g. the import / export pattern) is going to change in each upcoming month (see Table 1 for example). The ratio difference can be used to provide an improved value parameter for a shipment product.

[0061] For example, Table 1 shows an example port, an example time period (e.g. example month), an example first shipment product parameter (e.g. import revenue per FFE), an example second shipment product parameter (e.g. export revenue per FFE), an example ratio between the first and second shipment product parameter, a ratio difference called Delta between a first ratio (corresponding to the ratio of the previous month) and a second ratio (corresponding to the ratio of the current month), an example value change parameter (e.g. rate change percentage). Table 1 is for example associated with a shipment product. Table 1 is generated in June 2022, and predicts shipment product parameters for an upcoming period of 3 months: July, August, and September 2022.

[0062] Table 1 .

[0063] For example, the lmport_RpF is the import revenue per volume. The Export_RpF may be seen as the export revenue per volume. In other words, the lmport_RpF and / or the Export_RpF may be seen as one or more of the one or more shipment product parameters.

[0064] In some examples, the lmport_RpF of Table 1 from 2021-10 to 2022-06 may be part of historical data associated with a shipment product. In some examples, the lmport_RpF may be seen as the historical import revenue per volume. In some examples, the Export_RpF of Table 1 from 2021-10 to 2022-06 may be part of historical data associated with a shipment product. In some examples, the Export_RpF may be seen as the historical export revenue per volume.

[0065] In some examples, the lmport_RpF values of Table 1 from 2022-07 to 2022-09 may be seen as predicted shipment product parameters, such as predicted import revenues per volume. In some examples, the Export_RpF values of Table 1 from 2022-07 to 2022-09 may be seen as predicted shipment product parameters, such as predicted export revenues per volume.

[0066] In some example, the ratio of Table 1 of 2022-07 may be seen as the first ratio while the second ratio is ratio of 2022-08 for calculating the ratio difference of 2022-08. In some example, the ratio of Table 1 of 2022-08 may be seen as the first ratio while the second ratio is ratio of 2022-09 for calculating the ratio difference of 2022-09. The Ratio of Table 1 from 2022-07 to 2022-09 may be seen as the second ratio. The Delta of Table 1 may be seen as the ratio difference, rounded up to 0.1 for second decimals equal or above 0.05. The Rate Change Percentage of Table 1 may be seen as the value change parameter.

[0067] In one or more example methods, generating S106 the value change parameter comprises determining S106D the value change parameter based on the ratio difference. In some examples, determining the value change parameter comprises determining whether the ratio difference satisfies a criterion. For example, the criterion is based on one or more thresholds. In some examples, generating a value change parameter (e.g., the Rate Change Percentage of Table 1) comprises determining whether the ratio difference satisfies a criterion. A threshold is for example a value (e.g., an integer, a decimal, etc.). In some examples, a criterion comprises one or more thresholds. In some examples, a criterion comprises two thresholds. For example, the threshold is -5, -2, -1 , - 0.5, -0.1 , and / or 0. For example, the threshold is 5, 2, 1 , 0.5, 0.1 , and / or 0.

[0068] Table 2 shows example thresholds used for determining the value change parameter based on the ratio difference. For example, the criterion may include a first criterion, second criterion, a third criterion, a fourth criterion, a fifth criterion, a sixth criterion, a seventh criterion, and / or an eighth criterion.

[0069] Table 2.

[0070] The term “val” of Table 2 may denote the ratio difference (e.g., the Delta of Table 1 ). In some examples, the Rate Change Percentage of Table 2 is the same as the Rate Change Percentage of Table 1 . For example, the Rate Change Percentage of Table 1 is generated based on the thresholds shown in Table 2.

[0071] For example, a first criterion comprises a first threshold and a second threshold. For example, the first criterion is satisfied when the ratio difference (e.g., val of Table 2) is less than or equal to the first threshold and greater than the second threshold. For example, the first threshold is 0.00. For example, the second threshold is -0.1 . In some examples, the first criterion is satisfied when the ratio difference (e.g., val of Table 2) is between - 0.00 and -0.1 or equal to 0.00. In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the first criterion being satisfied, generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of 0 (e.g., 0%). In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the first criterion not being satisfied, not generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of 0 (e.g., 0%).

[0072] For example, a second criterion comprises a second threshold and a third threshold. For example, the second criterion is satisfied when the ratio difference (e.g., val of Table 2) is less than or equal to the second threshold and greater than the third threshold. For example, the second threshold is -0.1 . For example, the third threshold is -0.5. In some examples, the second criterion is satisfied when the ratio difference (e.g., val of Table 2) is between -0.1 and -0.5 or -0.1 . In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the second criterion being satisfied, generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of +7 (e.g., +7%). In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the second criterion not being satisfied, not generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of +7 (e.g., +7%).

[0073] For example, a third criterion comprises a third threshold and a fourth threshold. For example, the third criterion is satisfied when the ratio difference (e.g., val of Table 2) is less than or equal to the third threshold and greater than the fourth threshold. For example, the third threshold is -0.5. For example, the fourth threshold is -1 . In some examples, the third criterion is satisfied when the ratio difference (e.g., val of Table 2) is between -0.5 and -1 or equal to - 0.5. In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the third criterion being satisfied, generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of +12 (e.g., +12%). In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the third criterion not being satisfied, not generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of +12 (e.g., +12%).

[0074] For example, a fourth criterion comprises a fourth threshold. For example, the third criterion is satisfied when the ratio difference (e.g., val of Table 2) is less than the fourth threshold. For example, the fourth threshold is -1 . In some examples, the third criterion is satisfied when the ratio difference (e.g., val of Table 2) is less than -1 . In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the fourth criterion being satisfied, generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of +20 (e.g., +20%). In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the fourth criterion not being satisfied, not generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of +20 (e.g., +20%).

[0075] For example, a fifth criterion comprises a first threshold and a fifth threshold. For example, the fifth criterion is satisfied when the ratio difference (e.g., val of Table 2) is greater than or equal to the first threshold and less than the fifth threshold. For example, the first threshold is 0.00. For example, the fifth threshold is 0.1 . In some examples, the fifth criterion is satisfied when the ratio difference (e.g., val of Table 2) is between 0.00 and 0.1 or equal to 0.1 . In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the fifth criterion being satisfied, generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of 0 (e.g., 0%). In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the fifth criterion not being satisfied, not generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of 0 (e.g., 0%).

[0076] For example, a sixth criterion comprises a fifth threshold and a sixth threshold. For example, the sixth criterion is satisfied when the ratio difference (e.g., val of Table 2) is greater than or equal to the fifth threshold and less than the sixth threshold. For example, the fifth threshold is 0.1 . For example, the sixth threshold is 0.5. In some examples, the sixth criterion is satisfied when the ratio difference (e.g., val of Table 2) is between 0.1 and 0.5. In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the sixth criterion being satisfied, generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of -7 (e.g., -7%). In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the sixth criterion not being satisfied, not generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of -7 (e.g., - 7%).

[0077] For example, a seventh criterion comprises a sixth threshold and a seventh threshold. For example, the seventh criterion is satisfied when the ratio difference (e.g., val of Table 2) is greater than or equal to the sixth threshold and less than the seventh threshold. For example, the sixth threshold is 0.5. For example, the seventh threshold is 1. In some examples, the seventh criterion is satisfied when the ratio difference (e.g., val of Table 2) is between 0.5 and 1 . In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the seventh criterion being satisfied, generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of -12 (e.g., -12%). In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the seventh criterion not being satisfied, not generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of -12 (e.g., -12%).

[0078] For example, an eighth criterion comprises a seventh threshold. For example, the eighth criterion is satisfied when the ratio difference (e.g., val of Table 2) is greater than the seventh threshold. For example, the seventh threshold is 1 . In some examples, the eighth criterion is satisfied when the ratio difference (e.g., val of Table 2) is greater than 1 . In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the eighth criterion being satisfied, generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of -20 (e.g., -20%). In some examples, generating a value change parameter indicative of a change of a value associated with the shipment product comprises, in accordance with the eighth criterion not being satisfied, not generating a value change parameter (e.g., Rate Change Percentage of Table 1 and 2) of -20 (e.g., - 20%).

[0079] In one or more example methods, predicting S108, based on the historical data and the value change parameter, the selection parameter comprises applying S108A a machine learning model to the historical data and the value change parameter to generated the selection parameter. This allows for taking into account inventory availability, such as the availability of the one or more shipment products in the inventory. In one or more examples, the selection parameter is predicted by applying the machine learning model to one or more of: historical import and / or export revenue per volume, historical import and / or historical export revenue, historical revenue per volume ratio, a historical selection parameter per shipment product, a mean and / or median turnaround time, a mean and / or median import inventory availability and / or export inventory availability, and a mean and / or median inventory consumption for each shipment product parameter.

[0080] In one or more example methods, the machine learning model is a supervised machine learning model. A supervised machine learning model is for example a machine learning model trained based on labelled data sets. In one or more example methods, the machine learning model comprises one or more of: a linear regression, a Support Vector Machine, SVM, regressor, a Random Forest regressor, wherein each model is associated with a shipment product. In one or more example methods, the machine learning model is trained based on historical data and / or historical value change parameters and / or historical selection parameters. In some examples, the machine learning model can be seen as a pre-trained machine learning model. For example, the machine learning model can be (pre)trained once in a month using the historical rate change vs change in the selection parameter (such as adoption change data). The historical value change parameters may be indicative of historical change, over a period of time (such as a historical period of time), of a value associated with the shipment product. The historical value change parameters are for example, indicative of historical changes (e.g., past change) in value of the shipment product. In some examples, the method comprises obtaining historical value parameter (e.g., cost) and / or historical selection parameters associated with a shipment product. In some examples, the method comprises generating historical value change parameters based on the historical value parameters associated with a shipment product. For example, generating historical value change parameters based on the historical value parameter comprises calculating previous changes in the value parameter associated with a shipment product (e.g., the historical change in the value parameter from one month to another month). In some examples, the method comprises obtaining historical selection parameters corresponding to historical value change parameters associated with the shipment product. In some examples, the method comprises obtaining historical selection parameters corresponding with each historical value change parameter associated with a shipment product.

[0081] In some examples, predicting the selection parameter comprises inputting the value change parameter into the machine learning model (e.g., the pre-trained machine learning model). In some examples, the machine learning model (e.g., the pre-trained machine learning model) is configured to predict a selection parameter associated (e.g., corresponding with) with the value change parameter. In other words, the pre-trained machine learning model is configured to predict a selection parameter (e.g., a user adoption rate) of a shipment product associated (e.g., corresponding) with a value change parameter of the shipment product. In other words, for example, the historical data of value change parameters is used to predict a potential value change parameter (e.g. the percentage change in cost) and corresponding change in selection parameter for each shipment product.

[0082] In some examples, the method comprises inputting additional value change parameters to the machine learning model, such as potential value change parameters. Additional change value parameters are for example value change parameters different from the updated value parameter. For example, the additional value change parameters comprise values of a range for potential value change parameters. The additional value change parameters can be seen as an arbitrary range of values. The range of the additional value change parameters may for example be determined by the user.

[0083] In one or more example methods, determining S110 the updated value parameter associated with the shipment product comprises performing S110A a simulation of the updated value parameter based on one or more of: the historical data, the value change parameter, the one or more shipment product parameters, and the selection parameter. In some examples, determining the updated value parameter associated with the shipment product comprises performing (e.g., sequentially) one or more simulations per port and / or per month. In some examples, inputs for the simulation include the value change parameter and / or the corresponding selection parameters, the predicted shipment product parameters (e.g. import volume (e.g., FFE), export volume (e.g., FFE), variability associated with the export volume and / or the import volume), and historical data (e.g. mean and / or median import inventory availability and / or export inventory availability, and / or mean and / or median inventory consumption). In some examples, performing the simulation of the updated value parameter comprises performing the simulation for each shipment product (e.g., per port) associated with the shipment of an item. In some examples, the simulation may be performed for shipment products associated with import (e.g., time extension, such as free time extension) and / or associated with export (e.g., premium quality containers).

[0084] In one or more example methods, the simulation is a Monte Carlo simulation. In some examples, performing the simulation comprises providing a relation between the value change parameter and an inventory availability of the shipment product. In some examples, performing the simulation comprises performing the simulation for each of the shipment products associated with the shipment of an item.

[0085] In one or more example methods, the updated value data comprises the updated product parameter associated with the shipment product.

[0086] In some examples, performing the simulation comprises performing the simulation for the updated value parameter and one or more additional value change parameters associated with a shipment product. For example, performing the simulation comprises performing the simulation for each of the additional value change parameters associated with a shipment product. In some examples, performing the simulation comprises calculating an updated selection parameter, based on the historical selection parameter and the selection parameter, corresponding with a value of the shipment product. In some examples, performing the simulation comprises calculating, based on the variability parameter, shipment product parameters (e.g. a range of import volume (e.g., predicted) and / or export volume (e.g., predicted) per month). In some examples, performing the simulation comprises shipment product parameters (e.g. the import volume and / or the export volume) within the range defined and calculating the request for the given shipment product (e.g. PQC) from exporters using the selection parameter (e.g. adoption percentage change). In some examples, the availability of the shipment product can be randomized using mean / median and Monte Carlo simulation is run for 1000 iterations. For example the PQC import availability (count) is randomized using mean / median and the Monte Carlo simulation is run for 1000 iterations. The average of difference between shipment product requests (e.g. PQC demand) and shipment product availability for 1000 iterations is used for characterizing the impact on inventory availability of the shipment product due to corresponding updated value parameter.

[0087] In some examples, where the shipment product is a time extension, performing the Monte Carlo Simulation includes randomizing the import FFE’s within the range defined above and dividing the import FFE’s based on the selection parameter (e.g. new adoption percentage). The turn time for each import container is randomized based on mean / median of turn time for users who had selected a time extension and users who had not selected a time extension. In some examples, the Monte Carlo simulation is run for 1000 iterations to derive the total number of days taken to return the containers. The average of total number of days taken to return the containers generated by all iterations can be used for characterizing the impact on container inventory availability due to corresponding the updated value parameter for the shipment product being time extension. In some examples, the simulations are run for each value change parameter, e.g. for each cost change percentage value.

[0088] In some examples, the updated product data may be seen as the output of the simulation. In some examples, the output of the simulation comprises an updated value of a shipment product (e.g., a premium quality container, time extension), an updated selection parameter and / or a value indicative of the inventory available. In some examples, the output may differ depending on the user of the electronic device. For example, when the user is a price manager, the output may comprise an updated value parameter, an updated selection parameter and / or a value indicative of the inventory available.

[0089] In one or more example methods, determining S110 the updated value parameter associated with the shipment product comprises generating S110B, based on the simulated updated value parameter, the updated value parameter associated with the shipment product.

[0090] It may be appreciated that the disclosed technique has been tested for Q3 2022 based on historical data until Q2 2022 and the results of updated product data have been evaluated against the actual product data at 50 major ports. The results were found to be accurate for 42 ports.

[0091] Fig. 2 shows a block diagram of an exemplary electronic device 300 according to the disclosure. The electronic device 300 comprises memory circuitry 301 , processor circuitry 302, and an interface 303. The electronic device 300 is configured to perform any of the methods disclosed in Fig. 1 . In other words, the electronic device 300 is configured for updating product data of a shipment product associated with a shipment of an item.

[0092] In some examples, the electronic device is a shipment control device, such as a shipment product control device.

[0093] The electronic device 300 is configured to obtain (e.g., via memory circuitry 301 and / or interface 303) historical data associated with the shipment product.

[0094] The electronic device 300 is configured to determine (e.g., via the processor circuitry 302), based on the historical data, one or more shipment product parameters, by applying (e.g., via memory circuitry 301 and / or processor circuitry 302) a forecasting model to the historical data.

[0095] The electronic device 300 is configured to generate (e.g., via the processor circuitry 302), based on the one or more shipment product parameters, a value change parameter indicative of a change of a value associated with the shipment product.

[0096] The electronic device 300 is configured to predict (e.g., via the processor circuitry 302), based on the historical data and the value change parameter, a selection parameter indicative of a likelihood that a user selects the shipment product based on the value change parameter.

[0097] The electronic device 300 is configured to determine (e.g., via the processor circuitry 302) an updated value parameter associated with the shipment product based on one or more of: the historical data, the value change parameter, the one or more shipment product parameters, and the selection parameter.

[0098] The electronic device 300 is configured to provide (e.g., via the processor circuitry 302 and / or the interface 303) S112, based on the updated value parameter, updated product data associated with the shipment product.

[0099] The processor circuitry 302 is optionally configured to perform any of the operations disclosed in Fig. 1 (such as any one or more of: S102, S104, S104A, S106, S106A, S106B, S106C, S106D, S108, S108A, S110, S110A, S110B, S112). The operations of the electronic device 300 may be embodied in the form of executable logic routines (e.g., lines of code, software programs, etc.) that are stored on a non-transitory computer readable medium (e.g., the memory circuitry 301 ) and are executed by the processor circuitry 302).

[0100] Furthermore, the operations of the electronic device 300 may be considered a method that the electronic device 300 is configured to carry out. Also, while the described functions and operations may be implemented in software, such functionality may as well be carried out via dedicated hardware or firmware, or some combination of hardware, firmware and / or software.

[0101] The memory circuitry 301 may be one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, a random access memory (RAM), or other suitable device. In a typical arrangement, the memory circuitry 301 may include a non-volatile memory for long term data storage and a volatile memory that functions as system memory for the processor circuitry 302. The memory circuitry 301 may exchange data with the processor circuitry 302 over a data bus. Control lines and an address bus between the memory circuitry 301 and the processor circuitry 302 also may be present (not shown in Fig. 2). The memory circuitry 301 is considered a non-transitory computer readable medium. The memory circuitry 301 may be configured to store historical data, historical selection parameter, turnaround time, import inventory availability, export inventory availability, inventory consumption, one or more shipment product parameters, value change parameter, selection parameter, updated value parameter, updated product data, first forecasting model, first shipment product parameter, second forecasting model, second shipment product parameter, first ratio, first time period, second ratio, second time period, ratio difference, criterion, threshold, machine learning model and / or historical value change parameters in a part of the memory.

[0102] Embodiments of methods and products (electronic device) according to the disclosure are set out in the following items:

[0103] Item 1 . A method, performed by an electronic device, for updating product data of a shipment product associated with a shipment of an item, the method comprising: obtaining historical data associated with the shipment product; determining, based on the historical data, one or more shipment product parameters, by applying a forecasting model to the historical data; generating, based on the one or more shipment product parameters, a value change parameter indicative of a change of a value associated with the shipment product; predicting, based on the historical data and the value change parameter, a selection parameter indicative of a likelihood that a user selects the shipment product based on the value change parameter; determining an updated value parameter associated with the shipment product based on one or more of: the historical data, the value change parameter, the one or more shipment product parameters, and the selection parameter; and providing, based on the updated value parameter, updated product data associated with the shipment product. Item 2. The method according to item 1 , wherein the one or more shipment product parameters comprise one or more shipment product parameters per port and / or per time period.

[0104] Item 3. The method according to any of the previous items, wherein the one or more shipment product parameters comprise one or more of: revenue per volume, import revenue per volume, export revenue per volume, import volume, export volume, import and / or export volume pattern, a seasonality parameter, and a variability parameter.

[0105] Item 4. The method according to any of the previous items, wherein the forecasting model comprises a machine-learning based time-series forecasting model.

[0106] Item 5. The method according to any of the previous items, wherein the forecasting model comprises a first forecasting model for a first shipment product parameter and / or a second forecasting model for a second shipment product parameter.

[0107] Item 6. The method according to any of the previous items, wherein generating the value change parameter comprises: determining a first ratio between at least two shipment product parameters of the one or more shipment product parameters for a first time period; determining a second ratio between the at least two shipment product parameter of the one or more shipment product parameters for a second time period; determining a ratio difference based on a difference between the first ratio and the second ratio; and determining the value change parameter based on the ratio difference. Item 7. The method according to item 6, wherein the first time period precedes the second time period.

[0108] Item 8. The method according to any of the previous items, wherein predicting, based on the historical data and the value change parameter, the selection parameter comprises applying a machine learning model to the historical data and the value change parameter.

[0109] Item 9. The method according to item 8, wherein the machine learning model is a supervised machine learning model.

[0110] Item 10. The method according to any of items 8-9, wherein the machine learning model comprises one or more of: a linear regression, a Support Vector Machine regressor, and a Random Forest regressor, wherein each model is associated with a shipment product.

[0111] Item 11. The method according to any of items 8-10, wherein the machine learning model is trained based on historical data and / or historical value change parameters and / or historical selection parameters.

[0112] Item 12. The method according to any of the previous items, wherein determining the updated value parameter associated with the shipment product comprises: performing a simulation of the updated value parameter based on one or more of: the historical data, the value change parameter, the one or more shipment product parameters, and the selection parameter; and generating, based on the simulated updated value parameter, the updated value parameter associated with the shipment product. Item 13. The method according to item 10, wherein the simulation is a Monte Carlo simulation configured to randomize the one or more shipment product parameters for providing a relation between the value change parameter and an inventory availability of the shipment product.

[0113] Item 14. The method according to any of the previous items, wherein the updated product data comprises the updated value parameter associated with the shipment product.

[0114] Item 15. The method according to any of the previous items, wherein the value comprises a cost associated with the shipment product.

[0115] Item 16. An electronic device comprising memory circuitry, processor circuitry, and an interface, wherein the electronic device is configured to perform any of the methods according to any of items 1 -15.

[0116] Item 17. A computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by an electronic device cause the electronic device to perform any of the methods of items 1 -15.

[0117] The use of the terms “first”, “second”, “third” and “fourth”, “primary”, “secondary”, “tertiary” etc. does not imply any particular order, but are included to identify individual elements. Moreover, the use of the terms “first”, “second”, “third” and “fourth”, “primary”, “secondary”, “tertiary” etc. does not denote any order or importance, but rather the terms “first”, “second”, “third” and “fourth”, “primary”, “secondary”, “tertiary” etc. are used to distinguish one element from another. Note that the words “first”, “second”, “third” and “fourth”, “primary”, “secondary”, “tertiary” etc. are used here and elsewhere for labelling purposes only and are not intended to denote any specific spatial or temporal ordering. Furthermore, the labelling of a first element does not imply the presence of a second element and vice versa.

[0118] It may be appreciated that Figs. 1 -2 comprise some circuitries or operations which are illustrated with a solid line and some circuitries or operations which are illustrated with a dashed line. The circuitries or operations which are comprised in a solid line are circuitries or operations which are comprised in the broadest example embodiment. The circuitries or operations which are comprised in a dashed line are example embodiments which may be comprised in, or a part of, or are further circuitries or operations which may be taken in addition to the circuitries or operations of the solid line example embodiments. It should be appreciated that these operations need not be performed in order presented.

[0119] Furthermore, it should be appreciated that not all of the operations need to be performed. The exemplary operations may be performed in any order and in any combination.

[0120] It is to be noted that the word "comprising" does not necessarily exclude the presence of other elements or steps than those listed.

[0121] It is to be noted that the words "a" or "an" preceding an element do not exclude the presence of a plurality of such elements.

[0122] It should further be noted that any reference signs do not limit the scope of the claims, that the exemplary embodiments may be implemented at least in part by means of both hardware and software, and that several "means", "units" or "devices" may be represented by the same item of hardware.

[0123] The various exemplary methods, devices, nodes and systems described herein are described in the general context of method steps or processes, which may be implemented in one aspect by a computer program product, embodied in a computer- readable medium, including computer-executable instructions, such as program code, executed by computers in networked environments. A computer-readable medium may include removable and non-removable storage devices including, but not limited to, Read Only Memory (ROM), Random Access Memory (RAM), compact discs (CDs), digital versatile discs (DVD), etc. Generally, program circuitries may include routines, programs, objects, components, data structures, etc. that perform specified tasks or implement specific abstract data types. Computer-executable instructions, associated data structures, and program circuitries represent examples of program code for executing steps of the methods disclosed herein. The particular sequence of such executable instructions or associated data structures represents examples of corresponding acts for implementing the functions described in such steps or processes.

[0124] Although features have been shown and described, it will be understood that they are not intended to limit the claimed disclosure, and it will be made obvious to those skilled in the art that various changes and modifications may be made without departing from the scope of the claimed disclosure. The specification and drawings are, accordingly, to be regarded in an illustrative rather than restrictive sense. The claimed disclosure is intended to cover all alternatives, modifications, and equivalents.

Claims

CLAIMS1 . A method, performed by an electronic device, for updating product data of a shipment product associated with a shipment of an item, the method comprising: obtaining historical data associated with the shipment product; determining, based on the historical data, one or more shipment product parameters, by applying a forecasting model to the historical data; generating, based on the one or more shipment product parameters, a value change parameter indicative of a change of a value associated with the shipment product; predicting, based on the historical data and the value change parameter, a selection parameter indicative of a likelihood that a user selects the shipment product based on the value change parameter; determining an updated value parameter associated with the shipment product based on one or more of: the historical data, the value change parameter, the one or more shipment product parameters, and the selection parameter; and providing, based on the updated value parameter, updated product data associated with the shipment product.

2. The method according to claim 1 , wherein the one or more shipment product parameters comprise one or more shipment product parameters per port and / or per time period.

3. The method according to any of the previous claims, wherein the one or more shipment product parameters comprise one or more of: revenue per volume, import revenue per volume, export revenue per volume, import volume, export volume, import and / or export volume pattern, a seasonality parameter, and a variability parameter.

4. The method according to any of the previous claims, wherein the forecasting model comprises a machine-learning based time-series forecasting model.

5. The method according to any of the previous claims, wherein the forecasting model comprises a first forecasting model for a first shipment product parameter and / or a second forecasting model for a second shipment product parameter.

6. The method according to any of the previous claims, wherein generating the value change parameter comprises:- determining a first ratio between at least two shipment product parameters of the one or more shipment product parameters for a first time period;- determining a second ratio between the at least two shipment product parameter of the one or more shipment product parameters for a second time period;- determining a ratio difference based on a difference between the first ratio and the second ratio; and- determining the value change parameter based on the ratio difference.

7. The method according to claim 6, wherein the first time period precedes the second time period.

8. The method according to any of the previous claims, wherein predicting, based on the historical data and the value change parameter, the selection parameter comprises applying a machine learning model to the historical data and the value change parameter.

9. The method according to claim 8, wherein the machine learning model comprises one or more of: a linear regression, a Support Vector Machine regressor, and a Random Forest regressor, wherein each model is associated with a shipment product.

10. The method according to any of the previous claims, wherein determining the updated value parameter associated with the shipment product comprises:performing a simulation of the updated value parameter based on one or more of: the historical data, the value change parameter, the one or more shipment product parameters, and the selection parameter; and- generating, based on the simulated updated value parameter, the updated value parameter associated with the shipment product.

Images