Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A model construction method and a sales prediction method based on machine learning

A machine learning and construction method technology, applied in the field of machine learning, can solve problems such as uneven accuracy, and achieve the effect of improving forecast accuracy, accurate inventory management, and operation planning data

Inactive Publication Date: 2019-04-02
广州麦优网络科技有限公司
View PDF10 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Its advantages are fast and concise; the disadvantage is that the accuracy rate is uneven

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A model construction method and a sales prediction method based on machine learning
  • A model construction method and a sales prediction method based on machine learning
  • A model construction method and a sales prediction method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] In order to solve the uneven situation of the above-mentioned e-commerce field sales prediction expert method and the simple moving average statistical method accuracy rate; the present invention uses 3 models; LightGBM, WaveNet (CNN+DNN), LSTM to historical sales data (Time Series; time Sequence TS) is weighted as the final prediction model after prediction.

[0041] LightGBM: Predict the prediction target as a regression problem; in product sales forecasting, it can effectively combine discrete features such as product attributes (such as categories, periodicity) and continuous features of continuous sales through time sliding windows. The traditional moving average method can only extract time-related statistical features, and cannot process category features; at the same time, it cannot predict multiple commodities (Mulit_Step) at one time. Specific predictions such as Figure 5 , which can solve the problem of predicting multiple commodities at a time.

[0042] Wa...

Embodiment 2

[0054] Embodiment 2 discloses an electronic device, which includes a processor, a memory, and a program, wherein one or more processors and memories can be used, and the program is stored in the memory and configured to be executed by the processor, When the processor executes the program, the machine learning-based model building method of Embodiment 1 is realized. The electronic device may be a series of electronic devices such as a mobile phone, a computer, and a tablet computer.

Embodiment 3

[0056] Embodiment 3 discloses a computer-readable storage medium, the storage medium is used to store a program, and when the program is executed by a processor, the machine learning-based model building method of Embodiment 1 is implemented.

[0057] Of course, a storage medium containing computer-executable instructions provided by an embodiment of the present invention, the computer-executable instructions are not limited to the above-mentioned method operations, and can also perform related operations in the methods provided by any embodiment of the present invention .

[0058] Through the above description about the implementation mode, those skilled in the art can clearly understand that the present invention can be realized by means of software and necessary general-purpose hardware, and of course it can also be realized by hardware, but in many cases the former is a better implementation mode . Based on this understanding, the essence of the technical solution of the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a model construction method based on machine learning. The model construction method comprises a data processing step of processing received historical data of a product to obtain product statistical characteristics and promotion characteristics; a data transmission step of transmitting the product statistical characteristics and the promotion characteristics to an LGB model, a WaveNet model and an LSTM model for data processing; and a prediction model construction step of weighting the data processed by the LGB model, the WaveNet model and the LSTM model to obtain a prediction model. The invention also provides a sales prediction method based on machine learning. According to the model construction method based on machine learning, a final prediction model is formed by mixing a plurality of models such as a classic time sequence model and a deep learning model, so that the prediction accuracy of product sales is greatly improved, and more accurate inventory management and operation planning data can be provided for a user.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a machine learning-based model building method and a sales forecasting method. Background technique [0002] At present, in the field of Internet + e-commerce; the traditional method of predicting the sales of each product based on the experience of business experts is called the expert method. Its advantage is fast and concise; the disadvantage is that the accuracy rate is uneven. Because the accuracy of sales forecast has a decisive impact on inventory management and operation planning. Therefore, improving the prediction accuracy of product sales has become a technical problem to be solved urgently by those skilled in the art. [0003] The existing implementation plan has the following methods: as the agricultural product production and marketing decision-making method, device and system provided in the invention authorized patent CN201510133375.X, according to the ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06Q30/02G06N3/04G06N3/08
CPCG06N3/082G06Q30/0201G06Q30/0202G06N3/045
Inventor 蒋健波兰俊杰
Owner 广州麦优网络科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products