Store Visit And Menu Sales Prediction With Real-Time Sales Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional sales volume prediction technologies struggle with inaccuracies when predicting the sales volume for each menu, particularly when popular or unpopular items deviate from expectations, leading to difficulties in predicting sales states and potential sold-out scenarios.
Innovation Solution
A prediction device and method that utilize a store visit number prediction model to forecast store visits and sales rates, combined with a sales volume prediction unit that corrects sales volumes using stock data, to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional sales volume prediction technology is used, then prediction can be performed before business hours using external data, but prediction accuracy deteriorates when popular or unpopular menus deviate from expectations and when sold-out menus occur
Solution Approach 1:
The system performs preliminary prediction before business hours using historical data and external factors, then executes real-time correction during business hours based on actual sales state. This two-stage approach ensures both advance planning capability and adaptive accuracy.
Solution Approach 2:
The system incorporates real-time feedback from actual sales data during business hours to correct the preliminary prediction. By comparing predicted vs. actual sales rates and adjusting for sold-out items, the system continuously refines its accuracy throughout the business day.
2Device complexity
If prediction is performed using only historical data and external factors, then the system remains simple, but it cannot account for real-time sales state changes and sold-out scenarios
Solution Approach 1:
The system divides the prediction process into distinct segments: a preliminary prediction phase using historical data and external factors, and a real-time correction phase using actual sales state data. This segmentation allows each phase to focus on specific data types while maintaining overall system manageability.
Solution Approach 2:
The system transitions from a static prediction model to a dynamic one that adapts during business hours. The correction mechanism adjusts predictions based on real-time sales rate changes and sold-out conditions, making the system responsive to changing conditions without requiring complete redesign.
Data Source
AI summary
A prediction device includes: a store visit number prediction unit that acquires data regarding the number of past visits to a store, inputs the data to a trained store visit number prediction model, and predicts the number of visits to a store on a prediction target day by using an output from the store visit number prediction model; a rate prediction unit that acquires data regarding the number of past visits to a store, a past sales volume until a designated time of the prediction target day, and a sales time feature of the prediction target day, and predicts a sales rate of each product; and a sales volume prediction unit that predicts a sales volume of each product on the prediction target day by using the number of visits to a store predicted by the store visit number prediction unit and the sales rate of each product predicted by the rate prediction unit.