台灣零售業之業態競爭預測模型

Abstract

全球的零售業競爭越來越劇烈。因此，預測零售業態的競爭已成為一個重要的議題。然而，經濟成長和季節循環等因素顯著降低預測的準確性。對於零售業態的競爭受到經濟成長和季節性循環等因素的影響，本研究提出一種基於Lotka-Volterra模型的改良預測方法。同時依據市占率總和的限制，導出一個修正的Lotka-Volterra模型。此外，提出使用平均絕對誤差來評估市占率預測的精確度。本研究用台灣零售業營收資料（2000-2014年）來驗證提出的預測方法。我們的方法明確地顯示採用Lotka-Volterra模型時，資料前處理的重要性。零售業態的營收資料包含三個信號（成長、競爭和季節），在三個信號中，只包含競爭信號的資料預測準確性最佳，顯示Lotka-Volterra模型是競爭模型，使用的資料不該涵蓋多種信號。我們的方法可協助零售業者策略的發展和投資時機的決定，還顯示了如何運用Lotka-Volterra模型來預測產業的競爭。

The retail industry is an important component of the supply chain of the goods and services that are consumed daily and competition has been increasing among retailers worldwide. Thus, forecasting the degree of retail competition has become an important issue. However, economic growth and seasonal patterns in the level of retail activity dramatically reduce forecasting accuracy. This paper attempts to develop a forecasting methodology based on the Lotka–Volterra model for retail format competition subject to economic growth and seasonal patterns. A modified Lotka–Volterra model with an additional constraint on the summation of market share is proposed. In addition, the mean absolute error is used to measure the forecasting accuracy of the market share. Real-world Taiwanese retail data from 2000 is used to validate the proposed forecasting methods. Our methodology successfully indicates the importance of data pre-processing when using the Lotka–Volterra model. For revenue data of the retail format, out of the three signals (growth, competition and seasonal signals), the competition signal should be the only signal that is contained for the best Lotka–Volterra forecasting. Our methodology assists the retail format in the development of management strategies and the decision of investment timing. We also demonstrate how the Lotka–Volterra model can be used to forecast the degree of industry competition.