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

Medicine sales prediction method and medicine sales prediction system based on hybrid model

A hybrid model and model forecasting technology, which is applied in market forecasting, biological neural network models, marketing, etc., can solve the problems of low forecasting accuracy and achieve the effects of improving forecasting accuracy, better predicting drug sales, and facilitating popularization and application

Inactive Publication Date: 2016-09-28
CHONGQING UNIV
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, if we directly look for the development law of the historical monthly sales volume of drugs, then forecasting the monthly sales volume of drugs on this basis will cause the problem of low prediction accuracy.

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
  • Medicine sales prediction method and medicine sales prediction system based on hybrid model
  • Medicine sales prediction method and medicine sales prediction system based on hybrid model
  • Medicine sales prediction method and medicine sales prediction system based on hybrid model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] As shown in the figure, a method for predicting medicine sales based on a mixed model provided in this embodiment includes the following steps:

[0068] Build an ARIMA model;

[0069] Obtain the historical data sequence of drug sales and input it into the ARIMA model prediction to obtain the ARIMA model prediction error and ARIMA prediction results;

[0070] Establish BP neural network model;

[0071] Input the prediction error of the ARIMA model into the BP neural network model for prediction and obtain the prediction result of the BP neural network;

[0072] The prediction result is obtained by superimposing the ARIMA prediction result and the BP neural network prediction result.

[0073] The ARIMA model is established through the following steps:

[0074] Determine the autoregressive coefficient p of the historical data sequence of drug sales through the acf autocorrelation function;

[0075] Determine the number of differences d by using the diff difference func...

Embodiment 2

[0139] This embodiment provides a drug sales forecasting method based on BP neural network and ARIMA combination model. This method is aimed at the problem of low prediction accuracy only by single-item prediction methods based on traditional research methods or artificial neural networks. Such as figure 1 As shown, the implementation of the above prediction process in this embodiment can be implemented simply by using the R language.

[0140] Realize the technical scheme of the project of the present invention to make: first, use the diff difference function in the R language package to stabilize the original drug sales sequence, determine the difference number of times d, then use the acf autocorrelation function in the R language package to determine the auto-regression of the original drug sales sequence Coefficient p, and finally use the pacf partial autocorrelation function in the R language package to determine the number of moving average items in the original drug sa...

Embodiment 3

[0160] This implementation example uses the quarterly sales volume of streptomycin in my country's Heilongjiang Province from 1980 to 1985, which uses the quarterly sales volume of streptomycin from 1980 to 1984 as the training data, and the quarterly sales volume of streptomycin in 1985 as the test data.

[0161] The sample data is shown in Table 1, Table 1. Sample data (unit: ten thousand pieces)

[0162] 1 2 3 4 1980 110.672 113.685 128.301 85.935 1981 117.725 131.058 126.537 106.203 1982 143.946 133.739 115.436 97.001 1983 111.753 112.773 86.139 76.955 1984 98.684 103.113 110.837 70.918 1985 98.017 95.180 96.070 83.140

[0163] The specific prediction steps are as follows:

[0164] Determine the parameters p, d, q of the ARIMA(p,d,q) model, and use the obtained ARIMA model to predict the quarterly sales of streptomycin in 1985.

[0165] ①Use R language to load the sales volume of streptomycin in each quarte...

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 medicine sales forecasting method based on a BP neural network and an ARIMA combination model; the problem of low forecasting accuracy of a single forecasting method based on a traditional research method or an artificial neural network is solved. This method first uses the ARIMA model to predict the historical annual sales volume of a certain type of drug, and its linear law information is included in the prediction error of the ARIMA model, and then uses the BP neural network to predict the error of the ARIMA model so that its nonlinear law is included in the prediction error of the ARIMA model. In the prediction results of BP neural network. Finally, the prediction result of ARIMA and the prediction of BP neural network are added to obtain the prediction value of the combined prediction model; this method can overcome the defects of the time series method in predicting drug sales to a large extent, and significantly improve the prediction accuracy of drug sales; it can be compared Good forecasting of drug sales can be used as a method for predicting future drug sales; the process of predicting drug sales can be easily realized through Eviews software, which is practical and easy to promote and apply.

Description

technical field [0001] The invention relates to the field of sales of computer technology in the pharmaceutical industry, in particular to a prediction of sales volume of medicine based on a mixed ARIMA model and an artificial neural network model. Background technique [0002] As an important part of my country's social market economy, the pharmaceutical market has a significant impact on the sustainable development of the national economy. In pharmaceutical marketing, drug distribution is one of the important contents. It is of great significance for pharmaceutical companies to continuously improve the distribution quantity prediction method and improve the prediction accuracy. Through the prediction and analysis of drug sales, pharmaceutical companies can more reasonably determine the type and quantity of drug distribution, thereby reducing corporate costs and improving efficiency, which is a further step towards informatization; pharmaceutical companies can grasp the sal...

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): G06Q30/02G06N3/02
CPCG06Q30/0203G06N3/02
Inventor 李季申永飞
Owner CHONGQING UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com