Spot market price prediction with geographic and load-specific alignment in the freight industry

Abstract

A system may include a database storing historical data and a server, communicatively coupled to the database and including an electronic processor configured to receive, from a user interface, an origin, a destination, a load type, and a desired transportation date for a load, retrieve from the database, the historical data associated with the origin, the destination, and the load type, receive from an external data source, real-time data associated with the origin, the destination, the load type, and the desired transportation date, determine, using one or more machine learning models, a spot market price prediction for the load based on the origin, the destination, the load type, the desired transportation date, the historical data, and the real-time data, and transmit the spot market price prediction to a computing device.

Description

SPOT MARKET PRICE PREDICTION WITH GEOGRAPHIC AND LOAD-SPECIFIC ALIGNMENT IN THE FREIGHT INDUSTRYCROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims the benefit of, and priority to, U.S. Provisional Application No. 63 / 665,966, filed on June 28, 2024, the entire contents of which are incorporated herein by reference.FIELD

[0002] Embodiments described herein relate to predicting spot market prices for freight transportation, and, more particularly, to automatically aligning pricing with current market conditions for each geographical region and load category using real-time data integration, data analytics, and machine learning.SUMMARY

[0003] The freight market is a vital sector that relies heavily on accurate spot market price predictions. Spot market prices for freight transportation fluctuate based on supply and demand for specific routes, load types, and geographic locations. However, existing prediction methods often fail to capture these intricate dynamics, leading to inefficiencies and missed opportunities for both carriers and shippers. In particular, the inefficiencies for carriers and shippers may result in higher fuel use, and consequently, higher emission of greenhouse gases.

[0004] To address these problems, embodiments described herein provide, among other things, systems, and methods for spot market price prediction with geographic and loadspecific alignment in the freight industry. For example, embodiments presented herein ensure pricing alignment with current market conditions for each geographical region and load category. To overcome limitations in the existing solutions, embodiments presented herein incorporate geographic specificity, load category differentiation, trust scores, upper and lower bounds, and explainability.

[0005] The systems described herein consider data specific to each geographic location, including factors like historical price trends, fuel prices, prevailing weather conditions, and infrastructure limitations on specific routes. This allows for more precise localized predictions. The systems also differentiate pricing based on the specific load category (e.g., dry van, refrigerated, oversize) being transported. Different load types have varying demand and handling requirements, which impacts pricing and fuel use. In some aspects, for each prediction, a trust score (e.g., assigned on a scale) is generated. This enables negotiations to hone in on actual current market conditions. Some aspects include an upper and a lower bound for each prediction in line with the most recent market trends. In some aspects, the system provides for each prediction the highest impact variables used in making the prediction. This provides increased understanding to both shippers and carriers as to why a prediction is driven to the current value.

[0006] Embodiments presented herein improve over existing freight market price prediction methods by. most importantly, providing efficiencies for aligning freight shipping, which reduces fuel use, and consequently, reduces greenhouse gases. By incorporating geographic and load category data, the systems presented herein offer more accurate spot market price predictions, allowing carriers and shippers to make informed decisions. Accurate predictions enable both carriers and shippers to optimize their operations and resource allocation, leading to a more efficient freight market. In addition, improved price forecasting helps carriers minimize operational risks and allows shippers to negotiate more favorable rates.

[0007] In some aspects, the disclosure includes a system for predicting spot market freight shipping rates, the system including: a database storing historical data; and a server, communicatively coupled to the database and including an electronic processor configured to receive, from a user interface, an origin, a destination, a load type, and a desired transportation date for a load, retrieve from the database, the historical data associated with the origin, the destination, and the load type, receive from an external data source, real-time data associated with the origin, the destination, the load type, and the desired transportation date, determine, using one or more machine learning models, a spot market price prediction for the load based on the origin, the destination, the load type, the desired transportation date,the historical data, and the real-time data, and transmit the spot market price prediction to a computing device.

[0008] In some aspects, the disclosure includes a method for predicting spot market prices for freight shipping, the method including: receiving, with an electronic processor, an origin, a destination, a load type, and a desired transportation date for a load from a user interface; retrieving, with the electronic processor, historical data associated with the origin, the destination, and the load type from a database; receiving, with the electronic processor, real-time data associated with the origin, the destination, the load type, and the desired transportation date from an external data source; determining, with the electronic processor using one or more machine learning models, a spot market price prediction for the load based on the origin, the destination, the load ty pe, the desired transportation date, the historical data, and the real-time data; and transmitting, with the electronic processor, the spot market price prediction to a computing device.

[0009] In some aspects, the disclosure includes a non-transitory computer-readable medium including instructions that, when executed by an electronic processor, cause the electronic processor to perform a set of operations including: receiving an origin, a destination, a load type, and a desired transportation date for a load from a user interface; retrieving historical data associated with the origin, the destination, and the load type from a database; receiving real-time data associated with the origin, the destination, the load type, and the desired transportation date from an external data source; determining, using one or more machine learning models, a spot market price prediction for the load based on the origin, the destination, the load type, the desired transportation date, the historical data, and the real-time data; and transmitting the spot market price prediction to a computing device.

[0010] The systems, methods, and non-transitory computer-readable media presented herein for spot market price prediction in the freight industry consider geographic specificities and load category variations to provide improved accuracy, leading to a reduction in fuel use and emission of greenhouse gases.BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In the accompanying figures similar or the same reference numerals may be repeated to indicate corresponding or analogous elements. These figures, together with the detailed description, below are incorporated in and form part of the specification and serve to further illustrate various embodiments of concepts that include the claimed invention, and to explain various principles and advantages of those embodiments.

[0012] FIG. 1 is a block diagram schematically illustrating a system for predicting spot market prices for freight shipping with geographic and load-specific alignment, in accordance with various aspects of the disclosure.

[0013] FIG. 2 is a diagram schematically illustrating one example of the server, in accordance with various aspects of the disclosure.

[0014] FIG. 3 is a flowchart illustrating an example process for predicting spot market prices for freight shipping, in accordance with various aspects of the disclosure.

[0015] Skilled artisans will appreciate that elements in the figures are illustrated for simplicity and clarity and have not necessarily been drawn to scale. For example, the dimensions of some of the elements in the figures may be exaggerated relative to other elements to help improve understanding of embodiments of the present disclosure.

[0016] The sy stem, apparatus, and method components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the disclosure with details that will be readily apparent to those of ordinary7skill in the art having the benefit of the description herein.DETAILED DESCRIPTION

[0017] Before any embodiments are explained in detail, it is to be understood that the embodiments described herein are not limited in their application to the details of construction and the arrangement of components set forth in the following description or illustrated in the following drawings. Embodiments may be practiced or carried out in various ways.

[0018] FIG. 1 is a block diagram schematically illustrating a system 100 for predicting spot market prices for freight shipping with geographic and load-specific alignment, in accordance with various aspects of the disclosure. As illustrated in FIG. 1, the system 100 includes server 102, a data analytics engine 104, one or more machine learning models 106, and a database 108. The illustrated components may be coupled via one or more wired or wireless connections, including via a communications network 110. A suitable communications network 110 may be implemented using various local and wide area networks, for example, a Bluetooth™ network, a Wi-Fi™ network), the Internet, a land mobile radio network, a cellular data network, a Long Term Evolution (LTE) network, a 4G network, a 5G network, or combinations or derivatives thereof. It should be understood that the system 100 is provided as an example and, in some embodiments, the system 100 may include additional components. For example, the system 100 may include multiple servers 102, multiple databases 104, and the like.

[0019] The server 102. the data analytics engine 104, and the one or more machine learning models 106 working together form the spot market predictor, i.e., a predictor of spot market prices in freight shipping. In some aspects, the server 102, described in more detail herein, may implement the data analytics engine 104 and the one or more machine learning models 106 using a combination of hardware and software. In some aspects, the components may be separate computing resources (e.g., provided in one or more local or cloud-based computing instances) coupled by one or more suitable computer networks.

[0020] The spot market predictor uses data stored in the database 108 and the external data sources 112 to predict spot market prices for freight shipping, as described herein. After determining predicted spot market prices for freight shipping, the server 102 may store the predictions in the database 108, transmit them to a computing device 114 (e.g., which outputs (displays) the predictions for a user), transmit the predictions to another system, or combinations of the foregoing.

[0021] As illustrated in FIG. 1, the database 108 may be a database housed on a suitable database server communicatively coupled to and accessible by the server 102. In other examples, the database 108 may be part of a cloud-based database system external to the system 100 and accessible by the server 102 over one or more additional networks. In some examples, all or part of the database 108 may be locally stored on the server 102.

[0022] In some embodiments, as illustrated in FIG. 1, the database 108 electronically stores previous freight predictions, historical pricing data for freight shipping and fuel prices, historical weather data, transport route data, and load type data. It should be understood that, in some embodiments, the data stored in the database 108 is distributed among multiple databases that communicate with the server 102 and, optionally, each database may store specific data used by the server 102 as described herein.

[0023] In some aspects, the spot market predictor receives data from external data sources 112. External data sources include public and private online services providing, for example, current freight pricing data, current fuel pricing data, current weather data, weather forecasts, current infrastructure status data (e.g.. road closures, detours, traffic conditions, and the like), and planned infrastructure status data (e.g., planned closures or construction projects).

[0024] The one or more machine learning models 106 use machine learning to predict spot market rates by a predetermined date(e.g., predict spot market rates for the next week (seven days), the next month (twenty-eight days), or other suitable predetermined date). Machine learning generally refers to the ability of a computer program to learn without being explicitly programmed. In some embodiments, a computer program (for example, a learning engine) is configured to construct an algorithm based on inputs. Supervised learning involves presenting a computer program with example inputs and their desired outputs. The computer program is configured to learn a general rule that maps the inputs to the outputs from the training data it receives. Example machine learning engines include decision tree learning, association rule learning, artificial neural networks, classifiers, inductive logic programming, support vector machines, clustering, Bayesian networks, reinforcement learning, representation learning, similarity and metric learning, sparse dictionary learning, and genetic algorithms. Using these approaches, a computer program can ingest, parse, and understand data and progressively refine algorithms for data analytics.

[0025] In some examples, the one or more machine learning models 106 are trained on historical data encompassing route information, load characteristics, weather patterns, macroeconomic data (e.g., fuel pricing data), and past freight price trends. The one or more machine learning models 106, when trained, may then ingest current data to predict future spot market prices of freight shipping.

[0026] In some examples, when the one or more machine learning models 106 is a single machine learning model, the single trained machine learning model may achieve 60% accuracy when predicting the spot market prices for the following week and within 12% of the actual spot market price.

[0027] Additionally, in some examples, when the one or more machine learning models 106 is a plurality of machine learning models, the plurality of trained machine learning models may achieve 85% accuracy when predicting the spot market prices for the following week and within 12% of the actual spot market price. The plurality of trained machine learning models may be referred to as “an ensemble of models.”

[0028] The spot market predictor also incorporates real-time data into the prediction process. For example, the spot market predictor may integrate real-time information like traffic, fuel costs, and unexpected route closures provided from the external data sources 112 to dynamically adjust price predictions, reflecting ever-changing market conditions.

[0029] The real-time data and historical data (e.g., retrieved from the database 108) are analyzed by the data analytics engine 104. The data analytics engine 104 uses advanced data analytics techniques to identify complex relationships between various factors influencing spot market prices, leading to more accurate predictions. For example, the data analytics engine 104 may analyze historical weather and route information from the database 108 to map pricing trends to certain weather and traffic conditions. When the data analytics engine 104 identifies similar conditions in the real-time data, it can use the pricing trends to help predict current pricing. In some aspects, the results of the data analytics are used as an input to the one or more machine learning models 106. In some aspects, the results of the data analytics may be used to continuously train the one or more machine learning models 106.

[0030] The system 1 0 may implement a software application accessible via a user interface (e.g., presented on the computing device 114) or integrated into existing logistics platforms. Users can specify the origin, destination, load type, and desired transportation date to receive a customized price prediction for the spot market.

[0031] FIG. 2 is a diagram schematically illustrating one example of the server 1 2, in accordance with various aspects of the disclosure. In the illustrated example, the server 102 includes an electronic processor 202, a memory 204, and an input / output interface 206. Theelectronic processor 202. the memory 204, and the input / output interface 206. The illustrated components, along with other various modules and components are coupled to each other by or through one or more control and / or data buses that enable communication therebetween. The use of control and data buses for the interconnection between and exchange of information among the various modules and components would be apparent to a person skilled in the art in view of the description provided herein.

[0032] The electronic processor 202 obtains and provides information (e.g., from the memory 204 and / or the input / output interface 206), and processes the information byexecuting one or more software instructions or modules, capable of being stored, for example, in a random access memory (“RANT’) area of the memoiy 204 or a read only memory (“ROM”) of the memory 204 or another non-transitory computer readable medium (not shown). The software can include firmware, one or more applications, program data, filters, rules, one or more program modules, and other executable instructions. The electronic processor 202 is configured to retrieve from the memory 204 and execute, among other things, software related to the processes and methods described herein.

[0033] It should be further noted that, in some embodiments, the server 102 includes additional components which, for sake of brevity, are not discussed herein. Such components may include, for example, one or more human machine interfaces that enable a user to interact with and control the serv er 102 and other aspects of the system 100. For example, the serv er 102 may include a display (e.g., a liquid cry stal display (LCD) touch screen, an organic light-emitting diode (OLED) touch screen, and the like) and suitable physical or virtual selection mechanisms (e.g.. buttons, keys, knobs, switches, and the like). In some instances, the server 102 implements a graphical user interface (GUI) (e.g., generated by the electronic processor 202, from instructions and data stored in the memory' 204, and presented on a suitable display), that enables a user to interact with the server 102. In some embodiments, the GUI or other aspects of the system are presented by the server 102 remotely (e.g., on the computing device 114).

[0034] FIG. 3 is a flowchart illustrating an example process 300 for predicting spot market prices for freight shipping, in accordance with various aspects of the disclosure. FIG. 3 is described with respect to FIGS. 1 and 2.

[0035] The example process 300 includes receiving, with an electronic processor, an origin, a destination, a load type, and a desired transportation date for a load from a user interface (at block 302). For example, the electronic processor 202 receives an origin, a destination, a load type, and a desired transportation date for a load from a user interface.

[0036] The example process 300 includes retrieving, with the electronic processor, historical data associated with the origin, the destination, and the load type from a database (at block 304). For example, the electronic processor 202 retrieves historical data associated with the origin, the destination, and the load type from the database 108.

[0037] The example process 300 includes receiving, with the electronic processor, realtime data associated with the origin, the destination, the load type, and the desired transportation date from an external data source (at block 306). For example, the electronic processor 202 receives real-time data associated with the origin, the destination, the load type, and the desired transportation date from the external data sources 112.

[0038] The example process 300 includes determining, with the electronic processor using one or more machine learning models, a spot market price prediction for the load based on the origin, the destination, the load type, the desired transportation date, the historical data, and the real-time data (at block 308). For example, the electronic processor 202 determines, with the one or more machine learning models 106, a spot market price prediction for the load based on the origin, the destination, the load type, the desired transportation date, the historical data, and the real-time data.

[0039] The example process 300 also includes transmitting, with the electronic processor, the spot market price prediction to a computing device (at block 310). For example, the electronic processor 202 transmits the spot market price prediction to the computing device 114.

[0040] In some examples, receiving from the external data source, the real-time data associated with the origin, the destination, the load type, and the desired transportation date may further include dynamically, in real-time, receiving the real-time data associated with the origin, the destination, the load type, and the desired transportation date from the external data source.

[0041] In some examples, determining, using the one or more machine learning models, the spot market price prediction for the load based on the origin, the destination, the load type, the desired transportation date, the historical data, and the real-time data may further include dynamically, in real-time, determining, using one or more machine learning models, the spot market price prediction for the load based on the origin, the destination, the load type, the desired transportation date, the historical data, and the real-time data.

[0042] In some examples, transmitting the spot market price prediction to the computing device may further include dynamically, in real-time, transmitting the spot market price prediction to the computing device.

[0043] In some examples, the real-time data may include information regarding current freight prices, information regarding current fuel prices, information regarding current weather at and between the origin and the destination, information regarding current infrastructure at and between the origin and the destination, or a combination thereof. In these examples, the information regarding current infrastructure further includes cunent road closures, current detours, current traffic conditions, planned closures, planned construction projects, or a combination thereof. In some examples, the real-time data may include public data sources, private data sources, or a combination thereof.

[0044] In some examples, the historical data may include information regarding historical freight spot market predictions, information regarding historical freight prices, information regarding historical fuel prices, information regarding historical weather at and between the origin and the destination, information regarding historical infrastructure at and between the origin and the destination, information regarding historical routes between the origin and the destination, information regarding historical load types, or a combination thereof.

[0045] In some examples, the one or more machine learning models is a single trained machine learning model, and the spot market price prediction generated from the single trained machine learning model is within 12% of an actual spot market price for next week, at 65% accuracy.

[0046] In some examples, the one or more machine learning models is a plurality of trained machine learning models, and the spot market price prediction generated from theplurality of trained machine learning models is within 12% of an actual spot market price for next week, at 80% accuracy.

[0047] Example embodiments are herein described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to example embodiments. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a special purpose and unique machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. The methods and processes set forth herein need not, in some embodiments, be performed in the exact sequence as shown and likewise various blocks may be performed in parallel rather than in sequence. Accordingly, the elements of methods and processes are referred to herein as “blocks’’ rather than “steps.”

[0048] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function / act specified in the flowchart and / or block diagram block or blocks.

[0049] The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus that may be on or off-premises, or may be accessed via the cloud in any of a software as a service (SaaS), platform as a service (PaaS), or infrastructure as a service (laaS) architecture so as to cause a series of operational blocks to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide blocks for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. It is contemplated that any part of any aspect or embodiment discussed in this specification can be implemented or combined with any part of any other aspect or embodiment discussed in this specification.

[0050] In the foregoing specification, specific embodiments have been described. However, one of ordinary skill in the art appreciates that various modifications and changes can be made without departing from the scope of the invention as set forth in the claims below. Accordingly, the specification and figures are to be regarded in an illustrative rather than a restrictive sense, and all such modifications are intended to be included within the scope of present teachings. The benefits, advantages, solutions to problems, and any element(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential features or elements of any or all the claims. The invention is defined solely by the appended claims including any amendments made during the pendency of this application and all equivalents of those claims as issued.

[0051] Moreover, in this document, relational terms such as first and second, top and bottom, and the like may be used solely to distinguish one entity' or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms '‘comprises,” '‘comprising,” ‘'has,” “having,” “includes,” “including,” “contains,” “containing,” or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises, has. includes, contains a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by “comprises ... a,” '‘has .. . a,” “includes ... a,” or “contains ... a” does not, without more constraints, preclude the existence of additional identical elements in the process, method, article, or apparatus that comprises, has, includes, contains the element. Unless the context of their usage unambiguously indicates otherwise, the articles '‘a,” “an,” and “the” should not be interpreted as meaning '‘one” or “only one.” Rather these articles should be interpreted as meaning “at least one” or “one or more.” Likewise, when the terms “the” or “said” are used to refer to a noun previously introduced by the indefinite article “a” or “an,” “the” and “said” mean “at least one” or “one or more” unless the usage unambiguously indicates otherwise.

[0052] Also, it should be understood that the illustrated components, unless explicitly described to the contrary, may be combined or divided into separate software, firmware, and / or hardware. For example, instead of being located within and performed by a singleelectronic processor, logic and processing described herein may be distributed among multiple electronic processors. Similarly, one or more memory modules and communication channels or networks may be used even if embodiments described or illustrated herein have a single such device or element. Also, regardless of how they are combined or divided, hardware and software components may be located on the same computing device or may be distributed among multiple different devices. Accordingly, in this description and in the claims, if an apparatus, method, or system is claimed, for example, as including a controller, control unit, electronic processor, computing device, logic element, module, memory module, communication channel or network, or other element configured in a certain manner, for example, to perform multiple functions, the claim or claim element should be interpreted as meaning one or more of such elements where any one of the one or more elements is configured as claimed, for example, to make any one or more of the recited multiple functions, such that the one or more elements, as a set, perform the multiple functions collectively.

[0053] It will be appreciated that some embodiments may be comprised of one or more generic or specialized processors (or “processing devices”) such as microprocessors, digital signal processors, customized processors and field programmable gate arrays (FPGAs) and unique stored program instructions (including both software and firmware) that control the one or more processors to implement, in conjunction with certain non-processor circuits, some, most, or all of the functions of the method and / or apparatus described herein. Alternatively, some or all functions could be implemented by a state machine that has no stored program instructions, or in one or more application specific integrated circuits (ASICs), in which each function or some combinations of certain of the functions are implemented as custom logic. Of course, a combination of the two approaches could be used.

[0054] Moreover, an embodiment can be implemented as a computer-readable storage medium having computer readable code stored thereon for programming a computer (e.g., comprising a processor) to perform a method as described and claimed herein. Any suitable computer-usable or computer readable medium may be utilized. Examples of such computer- readable storage mediums include, but are not limited to, a hard disk, a CD-ROM, an optical storage device, a magnetic storage device, a ROM (Read Only Memory), a PROM (Programmable Read Only Memory), an EPROM (Erasable Programmable Read OnlyMemory), an EEPROM (Electrically Erasable Programmable Read Only Memory ) and a Flash memory. In the context of this document, a computer-usable or computer-readable medium may be any medium that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

[0055] Further, it is expected that one of ordinary skill, notwithstanding possibly significant effort and many design choices motivated by, for example, available time, current technology, and economic considerations, when guided by the concepts and principles disclosed herein will be readily capable of generating such software instructions and programs and ICs with minimal experimentation. For example, computer program code for carrying out operations of various example embodiments may be written in an object oriented programming language such as Java, Smalltalk, C++, Python, or the like. However, the computer program code for carry ing out operations of various example embodiments may also be written in conventional procedural programming languages, such as the ' C ' programming language or similar programming languages. The program code may execute entirely on a computer, partly on the computer, as a stand-alone software package, partly on the computer and partly on a remote computer or server or entirely on the remote computer or server. In the latter scenario, the remote computer or server may be connected to the computer through a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0056] The terms “substantially / ’ “essentially,” “approximately,” “about.” or any other version thereof, are defined as being close to as understood by one of ordinary skill in the art, and in one non-limiting embodiment the term is defined to be within 10%, in another embodiment within 5%, in another embodiment within 1% and in another embodiment within 0.5%. The term “one of,” without a more limiting modifier such as “only one of,” and when applied herein to two or more subsequently defined options such as “one of A and B” should be construed to mean an existence of any one of the options in the list alone (e.g., A alone or B alone) or any combination of two or more of the options in the list (e g., A and B together).

[0057] A device or structure that is “configured” in a certain way is configured in at least that way but may also be configured in ways that are not listed.

[0058] The terms ‘‘coupled,’' “coupling,” or “connected” as used herein can have several different meanings depending on the context in which these terms are used. For example, the terms coupled, coupling, or connected can have a mechanical or electrical connotation. For example, as used herein, the terms coupled, coupling, or connected can indicate that two elements or devices are directly connected to one another or connected to one another through intermediate elements or devices via an electrical element, electrical signal or a mechanical element depending on the particular context.

Claims

CLAIMSWhat is claimed is:

1. A system for predicting spot market freight shipping rates, the system comprising: a database storing historical data; and a server, communicatively coupled to the database and including an electronic processor configured to receive, from a user interface, an origin, a destination, a load type, and a desired transportation date for a load, retrieve from the database, the historical data associated with the origin, the destination, and the load type, receive from an external data source, real-time data associated with the origin, the destination, the load type, and the desired transportation date, determine, using one or more machine learning models, a spot market price prediction for the load based on the origin, the destination, the load type, the desired transportation date, the historical data, and the real-time data, and transmit the spot market price prediction to a computing device.

2. The system of claim 1, wherein, to receive from the external data source, the real-time data associated with the origin, the destination, the load type, and the desired transportation date, determine, using the one or more machine learning models, the spot market price prediction for the load based on the origin, the destination, the load type, the desired transportation date, the historical data, and the real-time data, and transmit the spot market price prediction to the computing device, the electronic processor is further configured to: dynamically, in real-time, receive from the external data source, real-time data associated with the origin, the destination, the load type, and the desired transportation date, dynamically, in real-time, determine, using one or more machine learning models, the spot market price prediction for the load based on the origin, the destination, the load type, the desired transportation date, the historical data, and the real-time data, and dynamically, in real-time, transmit the spot market price prediction to the computing device.

3. The system of claim 1, wherein the real-time data includes information regarding current freight prices, information regarding current fuel prices, information regarding current weather at and between the origin and the destination, information regarding cunent infrastructure at and between the origin and the destination, or a combination thereof.

4. The system of claim 3, wherein the real-time data include public data sources, private data sources, or a combination thereof, and wherein the information regarding current infrastructure further includes current road closures, current detours, current traffic conditions, planned closures, planned construction projects, or a combination thereof.

5. The system of claim 1, wherein the historical data includes information regarding historical freight spot market predictions, information regarding historical freight prices, information regarding historical fuel prices, information regarding historical weather at and between the origin and the destination, information regarding historical infrastructure at and between the origin and the destination, information regarding historical routes between the origin and the destination, information regarding historical load types, or a combination thereof.

6. The system of claim 1, wherein the one or more machine learning models is a single trained machine learning model, and wherein the spot market price prediction generated from the single trained machine learning model is within 12% of an actual spot market price at a predetermined date, at 65% accuracy.

7. The system of claim 1, wherein the one or more machine learning models is a plurality of trained machine learning models, and wherein the spot market price prediction generated from the plurality of trained machine learning models is within 12% of an actual spot market price at a predetermined date, at 80% accuracy.

8. A method for predicting spot market prices for freight shipping, the method comprising:receiving, with an electronic processor, an origin, a destination, a load type, and a desired transportation date for a load from a user interface; retrieving, with the electronic processor, historical data associated with the origin, the destination, and the load type from a database; receiving, with the electronic processor, real-time data associated with the origin, the destination, the load type, and the desired transportation date from an external data source; determining, with the electronic processor using one or more machine learning models, a spot market price prediction for the load based on the origin, the destination, the load type, the desired transportation date, the historical data, and the real-time data; and transmitting, with the electronic processor, the spot market price prediction to a computing device.

9. The method of claim 8, wherein, receiving from the external data source, the real-time data associated with the origin, the destination, the load ty pe, and the desired transportation date, determining, using the one or more machine learning models, the spot market price prediction for the load based on the origin, the destination, the load ty pe, the desired transportation date, the historical data, and the real-time data, and transmitting the spot market price prediction to the computing device further includes dynamically, in real-time, receiving the real-time data associated with the origin, the destination, the load type, and the desired transportation date from the external data source, dynamically, in real-time, determining, using one or more machine learning models, the spot market price prediction for the load based on the origin, the destination, the load type, the desired transportation date, the historical data, and the real-time data, and dynamically, in real-time, transmitting the spot market price prediction to the computing device.

10. The method of claim 8, wherein the real-time data includes information regarding current freight prices, information regarding current fuel prices, information regarding current weather at and between the origin and the destination, information regarding cunent infrastructure at and between the origin and the destination, or a combination thereof.

11. The method of claim 10, wherein the real-time data include public data sources, private data sources, or a combination thereof, and wherein the information regarding currentinfrastructure further includes current road closures, current detours, current traffic conditions, planned closures, planned construction projects, or a combination thereof.

12. The method of claim 8, wherein the historical data includes information regarding historical freight spot market predictions, information regarding historical freight prices, information regarding historical fuel prices, information regarding historical weather at and between the origin and the destination, information regarding historical infrastructure at and between the origin and the destination, information regarding historical routes between the origin and the destination, information regarding historical load types, or a combination thereof.

13. The method of claim 8, wherein the one or more machine learning models is a single trained machine learning model, and wherein the spot market price prediction generated from the single trained machine learning model is within 12% of an actual spot market price at a predetermined date, at 65% accuracy.

14. The method of claim 8, wherein the one or more machine learning models is a plurality of trained machine learning models, and wherein the spot market price prediction generated from the plurality of trained machine learning models is within 12% of an actual spot market price at a predetermined date, at 80% accuracy.

15. A non-transitory computer-readable medium comprising instructions that, when executed by an electronic processor, cause the electronic processor to perform a set of operations comprising: receiving an origin, a destination, a load type, and a desired transportation date for a load from a user interface; retrieving historical data associated with the origin, the destination, and the load type from a database; receiving real-time data associated with the origin, the destination, the load ty pe, and the desired transportation date from an external data source;determining, using one or more machine learning models, a spot market price prediction for the load based on the origin, the destination, the load ty pe, the desired transportation date, the historical data, and the real-time data; and transmitting the spot market price prediction to a computing device.

16. The non-transitory computer-readable medium of claim 15, wherein, receiving from the external data source, the real-time data associated with the origin, the destination, the load type, and the desired transportation date, determining, using the one or more machine learning models, the spot market price prediction for the load based on the origin, the destination, the load type, the desired transportation date, the historical data, and the real-time data, and transmitting the spot market price prediction to the computing device further includes dynamically, in real-time, receiving the real-time data associated with the origin, the destination, the load type, and the desired transportation date from the external data source, dynamically, in real-time, determining, using one or more machine learning models, the spot market price prediction for the load based on the origin, the destination, the load type, the desired transportation date, the historical data, and the real-time data, and dynamically, in real-time, transmitting the spot market price prediction to the computing device.

17. The non-transitory computer-readable medium of claim 15, wherein the real-time data includes information regarding current freight prices, information regarding current fuel prices, information regarding current weather at and between the origin and the destination, information regarding current infrastructure at and between the origin and the destination, or a combination thereof.

18. The non-transitory computer-readable medium of claim 17, wherein the real-time data include public data sources, private data sources, or a combination thereof, and wherein the information regarding current infrastructure further includes current road closures, current detours, current traffic conditions, planned closures, planned construction projects, or a combination thereof.

19. The non-transitory computer-readable medium of claim 15, wherein the one or more machine learning models is a single trained machine learning model, and wherein the spot market price prediction generated from the single trained machine learning model is within 12% of an actual spot market price at a predetermined date, at 65% accuracy.

20. The non-transitory computer-readable medium of claim 15. wherein the one or more machine learning models is a plurality of trained machine learning models, and wherein the spot market price prediction generated from the plurality of trained machine learning models is within 12% of an actual spot market price at a predetermined date, at 80% accuracy.

Images