A binary integer programming (BIP) model for optimal financial turning points detection

Abstract

Purpose This paper aims to detect the most profitable, i.e. optimal turning points (TPs), from the history of time series using a binary integer programming (BIP) model. TPs prediction problem is one of the most popular yet challenging topics in financial planning. Predicting profitable TPs results in earning profit by offering the opportunity to buy at low and selling at high. TPs detected from the history of time series will be used as the prediction model’s input. According to the literature, the predicted TPs’ profitability depends on the detected TPs’ profitability. Therefore, research for improving the profitability of detection methods has been never given up. Nevertheless, to the best of our knowledge, none of the existing methods can detect the optimal TPs. Design/methodology/approach The objective function of our model maximizes the profit of adopting all the trading strategies. The decision variables represent whether or not to detect the breakpoints as TPs. The assumptions of the model are as follows. Short-selling is possible. The time value for the money is not considered. Detection of consecutive buying (selling) TPs is not possible. Findings Empirical results with 20 data sets from Shanghai Stock Exchange indicate that the model detects the optimal TPs. Originality/value The proposed model, in contrast to the other methods, can detect the optimal TPs. Additionally, the proposed model, in contrast to the other methods, requires transaction cost as its only input parameter. This advantage reduces the process’ calculations.