Autoencoder based Hybrid Multi-Task Predictor Network for Daily Open-High-Low-Close Prices Prediction of Indian Stocks

TL;DR

This paper introduces a novel hybrid neural network combining an autoencoder and multi-task predictor for more accurate daily OHLC stock price prediction, especially handling sudden market changes and constraints.

Contribution

It proposes a pre-trained encoder cascaded with a multi-task predictor network to improve stock price forecasting accuracy and robustness against drastic market shifts.

Findings

The model predicts stock prices with high accuracy over 300 days.

It successfully recommends profitable stocks without losses during testing.

The approach outperforms traditional LSTM models in volatile market conditions.

Abstract

Stock prices are highly volatile and sudden changes in trends are often very problematic for traditional forecasting models to handle. The standard Long Short Term Memory (LSTM) networks are regarded as the state-of-the-art models for such predictions. But, these models fail to handle sudden and drastic changes in the price trend. Moreover, there are some inherent constraints with the open, high, low and close (OHLC) prices of the stocks. Literature lacks the study on the inherent property of OHLC prices. We argue that predicting the OHLC prices for the next day is much more informative than predicting the trends of the stocks as the trend is mostly calculated using these OHLC prices only. The problem mainly is focused on Buy-Today Sell-Tomorrow (BTST) trading. In this regard, AEs when pre-trained with the stock prices, may be beneficial. A novel framework is proposed where a pre-trained encoder is cascaded in front of the multi-task predictor network. This hybrid network can leverage the power of a combination of networks and can both handle the OHLC constraints as well as capture any sudden drastic changes in the prices. It is seen that such a network is much more efficient at predicting stock prices. The experiments have been extended to recommend the most profitable and most overbought stocks on the next day. The model has been tested for multiple Indian companies and it is found that the recommendations from the proposed model have not resulted in a single loss for a test period of 300 days.