A multi-stage machine learning approach for stock price prediction: Engineered and derivative indices

• A machine learning approach is proposed to predict the next day's stock prices, emphasizing innovative methodologies • A novel set of engineered and derivative indices for stock price prediction is proposed. • ANNs are employed to predict stock prices using both discrete and continuous indices derived from historical data. • A real case study including 5283 records of four stock prices from FTSE 100 is discussed. • The proposed methodology presents suitable applicability and accuracy. In this paper, a machine learning approach is proposed to predict the next day's stock prices. The methodology involves comprehensive data collection and feature generation, followed by predictions utilizing Multi-Layer Perceptron (MLP) networks. We selected 5,283 records of daily historical data, including open prices, close prices, highest prices, lowest prices, and trading volumes from four well-known stocks in the FTSE 100 index. A novel set of engineered and derivative indices is extracted from the original time series to enhance prediction accuracy. Two Multi-Layer Perceptron (MLP) are proposed to predict the next day's stock prices using the engineered discrete and continuous indices. The case study uses the daily historical time series of stock prices between January 1, 2000, and December 31, 2020. The proposed machine learning approach presents suitable applicability and accuracy, respectively.