Method of predicting initial input of new product, system for predicting initial input of new product, and recording medium

摘要

Based on numerical values with respect to factors influencing shares of existing products and a new product evaluated by more than one people, a structured neural network calculates predictive shares of the new product predicted by the respective persons (S6). Comprehensive evaluations on the respective products and the new product are calculated for each person, based on the numerical values with respect to the respective factors (S10). Correlation coefficients between the comprehensive evaluations on the respective products by the respective persons and the actual shares are calculated (S12), and relationships between the are obtained (S12). Predictive shares of the new product are calculated for the respective persons based on the relationships and the comprehensive evaluations on the new product (S16). The predictive shares are layered out in accordance with the correlation coefficients for the respective persons (S18). Average values of the predictive shares and confidence intervals are calculated for the respective layers (S20), and a share of the new product is predicted based on the average values and the confidence intervals for the respective layers and the calculation result obtained by the structured neural network.