Improving Long Short-Term Memory (LSTM)-Based Stock Market Price Predictions in the Machine Learning Era

Sarvesh Kumar, Nitin Pal, Aanjey Mani Tripathi

2024 · 16 citations · 10 references

Concepts

Abstract

Post covid, world especially India has seen enormous rise in stock market investor. Profits in stock market solely depends upon prediction – right prediction can help gain money. And predicting stock price can be very tedious task if done manually. Traditional methods are using stock price charts, exponential moving average (EMA), oscillators, indicators etc. While predicting stock price manually, human greed nature can lead to wrong decisions while choosing right stock. Latest technologies like machine learning and artificial intelligence can be used to predict future of stocks. Several research and works with different techniques have been already carried out to do the same. In this research explores a method, for predicting stock prices using machine learning, Long Short-Term Memory (LSTM) networks. These networks, which fall under the umbrella of learning provide a solution, by successfully capturing complex patterns from past stock data. As we explore the existing body of research and real-world implementations our goal is to participate in the discussion surrounding the utilization of machine learning, specifically LSTM networks to improve the precision and dependability of stock price forecasts. Looking ahead we anticipate a future where financial decision making becomes more informed and accurate.

References

10