Paper: arXiv 2311.09148

Abstract

Financial market forecasting remains a formidable challenge despite the surge in computational capabilities and machine learning advancements. While numerous studies have underscored the precision of computer-generated market predictions, many of these forecasts fail to yield profitable trading outcomes. This discrepancy often arises from the unpredictable nature of profit and loss ratios in the event of successful and unsuccessful predictions. In this study, we introduce a novel algorithm specifically designed for forecasting the profit and loss outcomes of trading activities. This is further augmented by an innovative approach for integrating these forecasts with previous predictions of market trends. This approach is designed for algorithmic trading, enabling traders to assess the profitability of each trade and calibrate the optimal trade size. Our findings indicate that this method significantly improves the performance of traditional trading strategies as well as algorithmic trading systems, offering a promising avenue for enhancing trading decisions.

Complexity vs Empirical Score

  • Math Complexity: 4.0/10
  • Empirical Rigor: 6.0/10 (capped from 7.0: transaction costs not modelled; see penalty flags)
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper introduces specific ML architectures and features (technical indicators) but relies on standard implementations and lacks theoretical derivations or novel proofs, resulting in moderate math complexity. The empirical rigor is high due to the use of real historical Bitcoin data, detailed preprocessing, clear train/validation/test splits, and the focus on a backtest-ready algorithmic trading strategy, though actual backtest performance metrics are not provided in the excerpt.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Predict Risk/Reward Ratio for Asset Management"] --> B["Data Input<br>Financial Market Data"]
  B --> C["Methodology Step 1<br>Forecast Profit/Loss Outcomes"]
  B --> D["Methodology Step 2<br>Integrate with Market Trend Predictions"]
  C --> E["Computational Process<br>Algorithmic Trading & Trade Sizing"]
  D --> E
  E --> F["Key Finding 1<br>Improved Traditional Strategy Performance"]
  E --> G["Key Finding 2<br>Enhanced Algorithmic Trading Systems"]

Cited References (36)

  1. Random walks and market efficiency tests: evidence on US, Chinese and European capital markets within the context of the global Covid-19 pandemic (2020)
  2. Impact of COVID-19 on stock market efficiency: Evidence from developed countries (2021)
  3. Technical analysis strategy optimization using a machine learning approach in stock market indices (2021)
  4. Investment Strategy Optimization Using Technical Analysis and Predictive Modeling in Emerging Markets (2015) — link
  5. The 10 reasons most machine learning funds fail (2018)
  6. A review of machine learning experiments in equity investment decision-making: why most published research findings do not live up to their promise in real life (2021)
  7. A CNN-BiLSTM-AM method for stock price prediction (2021)
  8. A survey of forex and stock price prediction using deep learning (2021)
and 28 more
  1. Prediction of stock price direction using a hybrid GA-XGBoost algorithm with a three-stage feature engineering process (2021)
  2. Classification-based financial markets prediction using deep neural networks (2017)
  3. Advances in financial machine learning (2018)
  4. Political uncertainty and stock returns: Evidence from the Brazilian political crisis (2019)
  5. From financial markets to Bitcoin markets: A fresh look at the contagion effect (2019)
  6. Fundamental analysis models in financial markets–review study (2015)
  7. News impact on stock price return via sentiment analysis (2014)
  8. Social-media and intraday stock returns: The pricing power of sentiment (2019)
  9. Persuasive evidence of market inefficiency (1998)
  10. What do we know about the profitability of technical analysis? (2007)
  11. Trends and applications of machine learning in quantitative finance (2019)
  12. The Kelly criterion in blackjack sports betting, and the stock market (2008)
  13. Evaluating multiple classifiers for stock price direction prediction (2015)
  14. Literature review: Machine learning techniques applied to financial market prediction (2019) — link
  15. A multiple support vector machine approach to stock index forecasting with mixed frequency sampling (2017) — link
  16. Evaluating machine learning classification for financial trading: An empirical approach (2016)
  17. Entropy and predictability of stock market returns (2002)
  18. An Exploratory Study on the Complexity and Machine Learning Predictability of Stock Market Data (2022)
  19. Photometric classification of type Ia supernovae in the SuperNova Legacy Survey with supervised learning (2016)
  20. Uncovering nonlinear structure in real-time stock-market indexes: the S&P 500, the DAX, the Nikkei 225, and the FTSE-100 (1997)
  21. Non-linear predictability of UK stock market returns (2003)
  22. Adaptive markets: Financial evolution at the speed of thought (2017)
  23. Correlation-based feature selection for machine learning (1999)
  24. Good and bad properties of the Kelly criterion (2010)
  25. Optimal betting under parameter uncertainty: Improving the Kelly criterion (2013)
  26. VaR: a tool to measure leverage risk (2003)
  27. Detecting concept drift in financial time series prediction using symbolic machine learning (1995)
  28. How Elon Musk’s twitter activity moves cryptocurrency markets (2023)

0 of 36 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.