Optimizing LSTM Based Network For Forecasting Stock Market

Ehsan Rokhsatyazdi · Shahryar Rahnamayan · Hossein Amirinia · S.M. Masum Ahmed

42 citations0/0 files storedIEEE Congress on Evolutionary Computation (CEC)

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Stock Market Forecasting Methods Forecasting Techniques and Applications Hydrological Forecasting Using AI

Abstract

In this modern era, the financial market, more specifically, the stock markets all over the world, deal with an enormous amount of real-time data that facilitates the data analytics and prediction in the field of finance. The main objective of this paper is to propose a novel model of neural network based on Long-Short Term Memory (LSTM) and utilizing one of the most powerful evolutionary algorithms, namely the Differential Evolution (DE), to forecast the next day's stock price of a company. This study focuses on optimizing the ten network hyperparameters related to the detection of temporal patterns of a given dataset, namely, the size of the time window, batch size, the number of LSTM units in hidden layers, the number of hidden layers (LSTM and dense), dropout coefficient for each layer, and the network training optimization algorithm. To the best of our knowledge, this is the first time that all this set of parameters have been optimized simultaneously. Then, the LSTM has been optimized by DE to gain the lower root mean squared error (RMSE) for prediction. The proposed model achieved 8.092 RMSE as its objective value, which is better in comparison with the best statistical forecasting models such as NAIVE, ETS, and SARIMA, which are the-state-of-the-art methods in this filed. Moreover, for shortening the training time as the main source of computational expensiveness, the proposed method works with a lower number of epochs. By this way, DE tries to find a shallower and faster network even with higher accuracy, which is a remarkable approach.

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

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

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 42 citations exist upstream.

References

1970EFFICIENT CAPITAL MARKETS: A REVIEW OF THEORY AND EMPIRICAL WORK*1982Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation 1970Efficient Capital Markets: A Review of Theory and Empirical Work 2018Statistical and Machine Learning forecasting methods: Concerns and ways forward 2001Application of support vector machines in financial time series forecasting 2017Stock price prediction using LSTM, RNN and CNN-sliding window model 2017Stock market's price movement prediction with LSTM neural networks 2008Surveying stock market forecasting techniques – Part II: Soft computing methods

Cited by

2021Prediction of Stock Market Index Using a Hybrid Technique of Artificial Neural Networks and Particle Swarm Optimization 2021Intelligent Asset Allocation using Predictions of Deep Frequency Decomposition

Explore the map →

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

Imported from OpenAlex (CC0) — nothing here is generated.