Comparison of ARIMA and Artificial Neural Networks Models for Stock Price Prediction

2014

567 citations recorded by the source corpus.

This paper examines the forecasting performance of ARIMA and artificial neural networks model with published stock data obtained from New York Stock Exchange. The empirical results obtained reveal the superiority of neural networks model over ARIMA model. The findings further resolve and clarify contradictory opinions reported in literature over the superiority of neural networks and ARIMA model and vice versa.

Subfields: Electrical and Electronic Engineering, Management Science and Operations Research

Citations in the corpus

• Which Artificial Intelligence Algorithm Better Predicts the Chinese Stock Market? (2018, neutral): “Among the many predictive efforts over the last few decades [1]–[3], some have had success using quantitative methods [4]–[9], such as autoregressive integrated moving average (ARIMA) models, artificial neural networks, support vector machine, and neuro-fuzzy based systems, but because of the nonlin”
• Listening to Chaotic Whispers: A Deep Learning Framework for News-oriented Stock Trend Prediction (2017, neutral): “With the development of deep learning, more research efforts have been paid on exploiting deep neural networks for financial prediction [2, 8, 12, 14, 21, 25].”
• Integrating metaheuristics and Artificial Neural Networks for improved stock price prediction (2016, unknown): “Adebiyi, Adewumi, and Ayo (2014) ound that 10 inputs obtained from the New York Stock Exchange ncluding open price, low price, high price, close price, and volume raded, 17 hidden neurons, and one output neuron give more accuate results in ANN model.”
• Stock Price Prediction via Discovering Multi-Frequency Trading Patterns (2017, unknown): “While there are many approaches to stock price prediction [2, 18, 23, 30], none of existing models, to our best knowledge, explicitly decompose trading patterns into various frequency components, and seamlessly integrate the discovered multi-frequency patterns into price predictions.”
• Temporal Relational Ranking for Stock Prediction (2018, unknown): “Traditional solutions for stock prediction are based on time-series analysis models, such as Kalman Filters [39], Autoregressive Models and their extensions [1].”
• A deep learning based stock trading model with 2-D CNN trend detection (2017, unknown): “to perform time-series analysis [1], [3], [4].”
• A Review of Deep Learning Models for Time Series Prediction (2019, unknown): “2923982 Integrated Moving Average (ARIMA) [4], [5], filtering-based methods [6], [7], support vector machines [8], etc.”