Employing Box-Plot based Fractional Grey Models for Forecasting New Product Short Demands

Abstract

The cost of investing in new product development is high and it is a feasible way to use demand forecasts from customer or end-users as a decisive reference However this short-term time series data has its learning difficulties In the past the fractional grey prediction model (fractional grey model FGM) has been proved that its cumulative method is better than the traditional integer cumulative of grey model (GM) model There are many researches using different optimal algorithms to determine the moderate score order And how to set the coefficient sets of ? in grey model is also worth exploring Therefore this research reveals a new grey model which used box plot to estimate the trend of data and combined this with FGM known as the box-plot-based fractional scale prediction model (box-plot-based FGM BFGM) to improve the accuracy of predictors by setting the coefficient sets of ? in traditional grey model In the experimental the examined dataset that collected from a well-known equipment manufacturer as the research object The result verified the effect through the commodity attributes and public test data of its production and the experimental results show that BFGM has better prediction results than FGM

Date of Award	2020
Original language	English
Supervisor	Der-Chiang Li (Supervisor)