Demand forecasting using weighted mixed machine learning models

Patent metadata

Field	Value
Publication number	US-2019130425-A1
Application number	US-201715799115-A
Country	US
Kind code	A1
Filing date	Oct 31, 2017
Priority date	Oct 31, 2017
Publication date	May 2, 2019
Grant date	—

Abstract

Embodiments forecast demand of an item by receiving historical sales data for the item for a plurality of past time periods including a plurality of features that define one or more feature sets. Embodiments use the feature sets as inputs to one or more different algorithms to generate a plurality of different models. Embodiments train each of the different models. Embodiments use each of the trained models to generate a plurality of past demand forecasts for each of some or all of the past time periods. Embodiments determine a root-mean-square error (“RMSE”) for each of the past demand forecasts and, based on the RMSE, determine a weight for each of the trained models and normalize each weight. Embodiments then generate a final demand forecast for the item for each future time period by combining a weighted value for each trained model.

First claim

What is claimed is:

1 . A method of forecasting demand of an item, the method comprising:
receiving historical sales data for the item for a plurality of past time periods, the historical sales data comprising a plurality of features that define one or more feature sets; using the feature sets as inputs to one or more different algorithms to generate a plurality of different models; training each of the different models with a same training set to generate a plurality of trained models; using each of the trained models, generating a plurality of past demand forecasts for each of some or all of the past time periods and generating a plurality of future demand forecasts for each of future time periods; determining a root-mean-square error (RMSE) for each of the past demand forecasts; based on the RMSE, determining a weight for each of the trained models and normalizing each weight; and generating a final demand forecast for the item for each future time periods by combining a weighted value for each trained model.

2 . The method of claim 1 , wherein the training the different models comprises using a machine learning algorithm for the training.

3 . The method of claim 2 , wherein the machine learning algorithm comprises one of linear regression, Support Vector Machine, or Artificial Neural Networks.

4 . The method of claim 1 , wherein the weight (W(i)) is determined from the RMSE (R(i)) as follows: (W(i)=1/R(i).

5 . The method of claim 4 , wherein each weight is normalized as follows:
W ′( i )= W ( i )/Σ j=1 m W ( j ).

6 . The method of claim 5 , wherein the final demand forecast (F′(x)) at week (x) comprises F′(x)=sum(w′(i)*f(i,x)).

7 . The method of claim 1 , wherein the final demand forecast is transmitted to a specialized inventory management system and a specialized manufacturing system.

8 . A computer-readable medium having instructions stored thereon that, when executed by a processor, cause the processor to forecast demand of an item, the forecast comprising:
receiving historical sales data for the item for a plurality of past time periods, the historical sales data comprising a plurality of features that define one or more feature sets; using the feature sets as inputs to one or more different algorithms to generate a plurality of different models; training each of the different models with a same training set to generate a plurality of trained models; using each of the trained models, generating a plurality of past demand forecasts for each of some or all of the past time periods and generating a plurality of future demand forecasts for each of future time periods; determining a root-mean-square error (RMSE) for each of the past demand forecasts; based on the RMSE, determining a weight for each of the trained models and normalizing each weight; and generating a final demand forecast for the item for each future time periods by combining a weighted value for each trained model.

9 . The computer-readable medium of claim 8 , wherein the training the different models comprises using a machine learning algorithm for the training.

10 . The computer-readable medium of claim 9 , wherein the machine learning algorithm comprises one of linear regression, Support Vector Machine, or Artificial Neural Networks.

11 . The computer-readable medium of claim 8 , wherein the weight (W(i)) is determined from the RMSE (R(i)) as follows: (W(i)=1/R(i).

12 . The computer-readable medium of claim 11 , wherein each weight is normalized as follows:
W ′( i )= W ( i )/Σ j=1 m W ( j ).

13 . The computer-readable medium of claim 12 , wherein the final demand forecast (F′(x)) at week (x) comprises F′(x)=sum(w′(i)*f(i,x)).

14 . The computer-readable medium of claim 8 , wherein the final demand forecast is transmitted to a specialized inventory management system and a specialized manufacturing system.

15 . A demand forecasting system comprising:
a processor coupled to a storage device that implements a demand forecasting module comprising;
receiving historical sales data for an item for a plurality of past time periods, the historical sales data comprising a plurality of features that define one or more feature sets;
using the feature sets as inputs to one or more different algorithms to generate a plurality of different models;
training each of the different models with a same training set to generate a plurality of trained models;
using each of the trained models, generating a plurality of past demand forecasts for each of some or all of the past time periods and generating a plurality of future demand forecasts for each of future time periods;
determining a root-mean-square error (RMSE) for each of the past demand forecasts;
based on the RMSE, determining a weight for each of the trained models and normalizing each weight; and
generating a final demand forecast for the item for each future time periods by combining a weighted value for each trained model.

16 . The system of claim 15 , wherein the training the different models comprises using a machine learning algorithm for the training.

17 . The system of claim 16 , wherein the machine learning algorithm comprises one of linear regression, Support Vector Machine, or Artificial Neural Networks.

18 . The system of claim 15 , wherein the weight (W(i)) is determined from the RMSE (R(i)) as follows: (W(i)=1/R(i).

19 . The system of claim 18 , wherein each weight is normalized as follows:
W ′( i )= W ( i )/Σ j=1 m W ( j ).

20 . The system of claim 19 , wherein the final demand forecast (F′(x)) at week (x) comprises F′(x)=sum(w′(i)*f(i,x)).

Assignees

• Oracle Int Corp

Inventors

• Lei Ming
• Popescu Catalin

Classifications

• G06Q30/0202 Primary

  Market predictions or forecasting for commercial activities · CPC title

• G06N99/005

  Physics · mapped topic

• G06Q30/0201

  Market modelling; Market analysis; Collecting market data · CPC title

• G06Q10/0631

  Resource planning, allocation, distributing or scheduling for enterprises or organisations · CPC title

• G06N20/00

  Machine learning · CPC title