High-Frequency Stock Trend Forecast Using LSTM Model

Abstract

The prediction of price trend in stock market is a challenging task due to the inherent complexity and dynamics in price movement. Many machine learning algorithms, such as Support Vector Machine, Artificial Neural Network, and Hidden Markov Model, have been applied to it and achieved positive results. Long Short-Term Memory (LSTM), as a variant of RNN, can obtain hidden dependencies in data and has shown a significant performance in processing time series data. In this paper, we apply LSTM networks to predict the price movement of a short-term and test it by an experiment on some stocks randomly selected from CSI 300 constituent stocks. The experiment shows that the precision, recall rate and critical error of LSTM are all better than that of the random prediction. It indicates that LSTM can be used in the trend prediction of stock price. We also notice that many improvements need to be done in future.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 47 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.