Multi-industry stock forecasting using GRU-LSTM deep transfer learning method

Abstract

After the Covid-19 pandemic, the number of investors in Indonesia has proliferated. In managing a good stock portfolio, investors need the right strategy too. One approach that can be applied is to predict stock movements by considering the company's industrial sector. This paper proposed a new framework for applying deep transfer learning for stock forecasting in multi-industry. The model used in the framework is a combined algorithm between Gated Recurrent Unit (GRU) and Long-Short Term Memory (LSTM). The author built the pre-trained model using Indeks Harga Saham Gabungan (IHSG) and transferred it to predict Indonesia's stock indexes based on industry classification (IDX-IC) as the measurer of stock movement in multiple industries. The outcomes reveal that this framework produces good model predictions and can be used to help analyze the evaluation of the pre-trained model to conduct transfer learning stock prediction in different industries efficiently. The model built using the IHSG indexes can predict stock prices best in the energy, technology, and industrial sectors.