Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash 105 tok/s
Gemini 2.5 Pro 52 tok/s Pro
GPT-5 Medium 45 tok/s
GPT-5 High 34 tok/s Pro
GPT-4o 108 tok/s
GPT OSS 120B 473 tok/s Pro
Kimi K2 218 tok/s Pro
2000 character limit reached

Mean Absolute Directional Loss as a New Loss Function for Machine Learning Problems in Algorithmic Investment Strategies (2309.10546v1)

Published 19 Sep 2023 in q-fin.CP, cs.AI, cs.LG, q-fin.GN, and q-fin.PM

Abstract: This paper investigates the issue of an adequate loss function in the optimization of machine learning models used in the forecasting of financial time series for the purpose of algorithmic investment strategies (AIS) construction. We propose the Mean Absolute Directional Loss (MADL) function, solving important problems of classical forecast error functions in extracting information from forecasts to create efficient buy/sell signals in algorithmic investment strategies. Finally, based on the data from two different asset classes (cryptocurrencies: Bitcoin and commodities: Crude Oil), we show that the new loss function enables us to select better hyperparameters for the LSTM model and obtain more efficient investment strategies, with regard to risk-adjusted return metrics on the out-of-sample data.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (21)
  1. Backtest overfitting in financial markets. Automated Trader, 2016a.
  2. The probability of backtest overfitting. Journal of Computational Finance, forthcoming, 2016b.
  3. Q. Bui and R. Ślepaczuk. Applying hurst exponent in pair trading strategies on nasdaq 100 index. Physica A: Statistical Mechanics and its Applications, page 126784, 2021. ISSN 0378-4371. doi: https://doi.org/10.1016/j.physa.2021.126784. URL https://www.sciencedirect.com/science/article/pii/S037843712100964X.
  4. G. M. Caporale and A. Plastun. The day of the week effect in the cryptocurrency market. Finance Research Letters, 31, 2019. ISSN 1544-6123. doi: https://doi.org/10.1016/j.frl.2018.11.012. URL https://www.sciencedirect.com/science/article/pii/S1544612318304240.
  5. A q-learning agent for automated trading in equity stock markets. Expert Systems with Applications, 163:113761, 2021. ISSN 0957-4174. doi: https://doi.org/10.1016/j.eswa.2020.113761. URL https://www.sciencedirect.com/science/article/pii/S0957417420305856.
  6. E. Chan. Algorithmic trading: winning strategies and their rationale, volume 625. John Wiley & Sons, 2013.
  7. E. P. Chan. Quantitative trading: how to build your own algorithmic trading business. John Wiley & Sons, 2021.
  8. L. Di Persio and O. Honchar. Artificial neural networks architectures for stock price prediction: Comparisons and applications. International Journal of Circuits, Systems And Signal Processing, 10:403–413, Jan. 2016.
  9. Technical trading rules in the cryptocurrency market. Finance Research Letters, 32:101396, 2020. ISSN 1544-6123. doi: https://doi.org/10.1016/j.frl.2019.101396. URL https://www.sciencedirect.com/science/article/pii/S1544612319308852.
  10. S. Hochreiter and J. Schmidhuber. Long Short-Term Memory. Neural Computation, 9(8):1735–1780, Nov. 1997. ISSN 0899-7667. doi: 10.1162/neco.1997.9.8.1735. URL https://doi.org/10.1162/neco.1997.9.8.1735.
  11. S. Jansen. Machine Learning for Algorithmic Trading: Predictive models to extract signals from market and alternative data for systematic trading strategies with Python. Packt Publishing Ltd, 2020.
  12. Momentum and contrarian effects on the cryptocurrency market. Physica A: Statistical Mechanics and its Applications, 523:691–701, June 2019. ISSN 0378-4371. doi: 10.1016/j.physa.2019.02.057. URL https://www.sciencedirect.com/science/article/pii/S037843711930216X.
  13. M. Lopez de Prado. What to look for in a backtest. Available at SSRN, 2013.
  14. A. Raudys. Portfolio of global futures algorithmic trading strategies for best out-of-sample performance. In International Conference on Business Information Systems, pages 424–435. Springer, 2016.
  15. M. Topcu and O. S. Gulal. The impact of covid-19 on emerging stock markets. Finance Research Letters, 36:101691, 2020. ISSN 1544-6123. doi: https://doi.org/10.1016/j.frl.2020.101691. URL https://www.sciencedirect.com/science/article/pii/S1544612320306966.
  16. A. Vo and C. Yost-Bremm. A high-frequency algorithmic trading strategy for cryptocurrency. Journal of Computer Information Systems, 60(6):555–568, 2020.
  17. N. Vo and R. Ślepaczuk. Applying hybrid arima-sgarch in algorithmic investment strategies on s&p500 index. Entropy, 24(2), 2022. ISSN 1099-4300. doi: 10.3390/e24020158. URL https://www.mdpi.com/1099-4300/24/2/158.
  18. All that glitters is not gold: Comparing backtest and out-of-sample performance on a large cohort of trading algorithms. The Journal of Investing, 25(3):69–80, 2016.
  19. Deep Learning for Stock Selection Based on High Frequency Price-Volume Data. arXiv:1911.02502 [cs, q-fin], Nov. 2019. URL http://arxiv.org/abs/1911.02502. arXiv: 1911.02502.
  20. Multi Factor Stock Selection Model Based on LSTM. International Journal of Economics and Finance, 10(8):1–36, 2018. URL https://ideas.repec.org/a/ibn/ijefaa/v10y2018i8p36.html. Publisher: Canadian Center of Science and Education.
  21. Investment Strategies that Beat the Market. What Can We Squeeze from the Market? Financial Internet Quarterly (formerly e-Finanse), 14(4):36–55, 2018. URL https://ideas.repec.org/a/vrs/finiqu/v14y2018i4p36-55n8.html. Publisher: Sciendo.
Citations (3)
View on Semantic Scholar
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Dice Question Streamline Icon: https://streamlinehq.com

Follow-up Questions

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now