Comparative analysis of neural network architectures for short-term FOREX forecasting

Paper: arXiv 2405.08045

Authors: Theodoros Zafeiriou, Dimitris Kalles

Abstract

The present document delineates the analysis, design, implementation, and benchmarking of various neural network architectures within a short-term frequency prediction system for the foreign exchange market (FOREX). Our aim is to simulate the judgment of the human expert (technical analyst) using a system that responds promptly to changes in market conditions, thus enabling the optimization of short-term trading strategies. We designed and implemented a series of LSTM neural network architectures which are taken as input the exchange rate values and generate the short-term market trend forecasting signal and an ANN custom architecture based on technical analysis indicator simulators We performed a comparative analysis of the results and came to useful conclusions regarding the suitability of each architecture and the cost in terms of time and computational power to implement them. The ANN custom architecture produces better prediction quality with higher sensitivity using fewer resources and spending less time than LSTM architectures. The ANN custom architecture appears to be ideal for use in low-power computing systems and for use cases that need fast decisions with the least possible computational cost.

Complexity vs Empirical Score

• Math Complexity: 3.5/10
• Empirical Rigor: 5.0/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper presents an applied benchmark comparing standard LSTM models with an indicator-based custom ANN for short-term FX prediction. It lacks theoretical math or advanced quantitative derivations, focusing instead on empirical computational efficiency and predictive heuristic performance. While practical for low-power trading applications, the novelty and statistical rigor remain modest.

Research Flowchart

  flowchart TD
    A[Goal: Optimize Short-Term FOREX Trading Signals] --> B[Data Inputs: FX Exchange Rates & Technical Analysis Indicators]
    B --> C{Model Development}
    C --> D[LSTM Neural Networks]
    C --> E[Custom ANN with Technical Indicator Simulators]
    D & E --> F[Benchmarking & Comparative Analysis]
    F --> G[Key Outcome: Custom ANN achieves superior prediction quality & higher sensitivity with lower computational cost]

Cited References (25)

1. Neural Networks and Statistical Techniques in Marketing Research (1994) — link
2. Intelligent stock trading system based on improved technical analysis and Echo State Network (2011) — link
3. Predicting stock market index using fusion of machine learning techniques (2014) — link
4. Automated Trading with Machine Learning on Big Data (2014) — link
5. SHORT-TERM TREND PREDICTION OF FOREIGN EXCHANGE RATES WITH A NEURAL-NETWORK BASED ENSEMBLE OF FINANCIAL TECHNICAL INDICATORS (2013) — link
6. The use of technical analysis in the foreign exchange market (1992) — link
7. Intelligent technical analysis based equivolume charting for stock trading using neural networks (2006) — link
8. Non-traditional methods of forecasting (1996) — link

0 of 25 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.