Why Existing Machine Learning Methods Fails At Extracting the Information of Future Returns Out of Historical Sctock Prices : the Curve-Shape-Feature and Non-Curve-Shape-Feature Modes

TL;DR

This paper investigates why current machine learning methods fail to predict future stock returns from historical data, revealing that most information is not contained in shape features and new models are needed for non-shape features.

Contribution

The study introduces pre-designed modes of correlation between future returns and historical prices, demonstrating the limitations of existing algorithms in capturing non-shape feature information.

Findings

Existing algorithms excel at shape feature extraction but fail on non-shape features.

Future returns are not primarily correlated with curve-shape features.

New models are required to analyze non-shape feature modes in financial data.

Abstract

The financial time series analysis is important access to touch the complex laws of financial markets. Among many goals of the financial time series analysis, one is to construct a model that can extract the information of the future return out of the known historical stock data, such as stock price, financial news, and e.t.c. To design such a model, prior knowledge on how the future return is correlated with the historical stock prices is needed. In this work, we focus on the issue: in what mode the future return is correlated with the historical stock prices. We manually design several financial time series where the future return is correlated with the historical stock prices in pre-designed modes, namely the curve-shape-feature (CSF) and the non-curve-shape-feature (NCSF) modes. In the CSF mode, the future return can be extracted from the curve shapes of the historical stock prices. By applying various kinds of existing algorithms on those pre-designed time series and real financial time series, we show that: (1) the major information of the future return is not contained in the curve-shape features of historical stock prices. That is, the future return is not mainly correlated with the historical stock prices in the CSF mode. (2) Various kinds of existing machine learning algorithms are good at extracting the curveshape features in the historical stock prices and thus are inappropriate for financial time series analysis although they are successful in the image recognition and natural language processing. That is, new models handling the NCSF series are needed in the financial time series analysis.