Skip to content

RESEARCH_REPORT.md

Latest commit

 

History

History
115 lines (88 loc) · 8.81 KB

RESEARCH_REPORT.md

File metadata and controls

115 lines (88 loc) · 8.81 KB
Raw

Research Report — 2026-05-04

Sources scanned: 6/10 AI summaries: NO (keyword-based)

[FAILED] ML in Financial Markets (ResearchGate - Grilli)

URL: https://www.researchgate.net/profile/Luca-Grilli/publication/358005792_Machine_learning_in_financial_markets/links/61ee9af44393577eca8a23e2/Machine-learning-in-financial-markets.pdf

[FAILED] Neural Networks for Trading (Academia.edu)

URL: https://www.academia.edu/download/104983274/11296.pdf

[OK] Algorithmic Trading MSc Thesis (UniVe)

URL: https://unitesi.unive.it/bitstream/20.500.14247/14114/1/870146-1273960.pdf

Key excerpts from Algorithmic Trading MSc Thesis (UniVe):

  • 2.2.4 Mean Reversion ............................................................................................ 35

  • strategies. These types of funds merge mathematical and statistical models with

  • shifts past and above the double exponential moving average. Synchronously, he sets a

  • sell order if the stock price goes beneath the double exponential moving average. In this

  • obtain small returns through a multitude of operations buying or selling following small price

  • DIAMOND: 2.2.4 Mean Reversion ............................................................................................ 35

  • DIAMOND: strategies. These types of funds merge mathematical and statistical models with

  • DIAMOND: shifts past and above the double exponential moving average. Synchronously, he sets a

[OK] ML Trading Strategies Review (MECS Press)

URL: https://www.mecs-press.org/ijeme/ijeme-v13-n6/IJEME-V13-N6-5.pdf

Key excerpts from ML Trading Strategies Review (MECS Press):

  • remain, ML creates valuable opportunities for ATS via alternative data sources, advanced feature engineering,

  • machine learning algorithms like neural networks, support vector machines, and random forests can be trained, and their

  • automated trading system, including components for order execution, risk management, and position sizing. This

  • OR "deep learning" AND "portfolio optimization" AND "neural networks" AND "trading strategies" AND

  • "overfitting" AND "high frequency trading" AND "risk management"

  • DIAMOND: remain, ML creates valuable opportunities for ATS via alternative data sources, advanced feature engineering,

  • DIAMOND: machine learning algorithms like neural networks, support vector machines, and random forests can be trained, and their

  • DIAMOND: automated trading system, including components for order execution, risk management, and position sizing. This

[OK] ML for Algorithmic Trading (Sciendo / REMAV)

URL: https://sciendo.com/pdf/10.2478/remav-2022-0021

Key excerpts from ML for Algorithmic Trading (Sciendo / REMAV):

  • – the unit price of property with the least favorable feature states.

  • – the unit price of a property with the most favorable feature states,

  • – one variables (“1” indicates the presence of a given feature state). We only have information that a

  • was introduced into the model as a single variable, because it is a quantitative feature.

  • these variables on the unit price of the property. Hence, for three property features (neighborhood,

  • DIAMOND: – the unit price of property with the least favorable feature states.

  • DIAMOND: – the unit price of a property with the most favorable feature states,

  • DIAMOND: – one variables (“1” indicates the presence of a given feature state). We only have information that a

[OK] Systematic Review Algorithmic Trading (AIPress VSE)

URL: http://aip.vse.cz/artkey/aip-202503-0013_systematic-review-on-algorithmic-trading.php

Key excerpts from Systematic Review Algorithmic Trading (AIPress VSE):

  • Fouque, J., Jaimungal, S., & Saporito, Y. F. (2022). Optimal Trading with Signals and Stochastic Price Impact. SIAM Journal on Financial Mathematics, 13(3), 944-968. https://doi.org/10.1137/21m1394473

  • Shafiq, S., Qureshi, S. S., & Akbar, M. (2023). Dynamic relationship of volatility of returns across different markets: evidence from selected next 11 countries. Journal of Economic and Administrative Sciences, (in press). https://doi.org/10.1108/jeas-09-2022-0216

  • Pemy, M., & Zhang, N. (2023). Optimal liquidation of a basket of stocks using reinforcement learning. In 2023 Proceedings of the Conference on Control and its Applications (CT) (pp. 41-47). Society for Industrial and Applied Mathematics. https://doi.org/10.1137/1.9781611977745.6

  • Merkin, L. A., & Rezin, R. M. (2022). On approximation of transition densities in calibration of 1-Dimensional stochastic models of asset prices. Lobachevskii Journal of Mathematics, 43(2), 429-442. https://doi.org/10.1134/s1995080222050183

  • Liu, P. (2023b). Seeking Better Sharpe Ratio via Bayesian Optimization. The Journal of Portfolio Management, 49(7), 35-43. https://doi.org/10.3905/jpm.2023.1.497

  • DIAMOND: Fouque, J., Jaimungal, S., & Saporito, Y. F. (2022). Optimal Trading with Signals and Stochastic Price Impact. SIAM Journal on Financial Mathematics, 13(3), 944-968. https://doi.org/10.1137/21m1394473

  • DIAMOND: Shafiq, S., Qureshi, S. S., & Akbar, M. (2023). Dynamic relationship of volatility of returns across different markets: evidence from selected next 11 countries. Journal of Economic and Administrative Sciences, (in press). https://doi.org/10.1108/jeas-09-2022-0216

  • DIAMOND: Pemy, M., & Zhang, N. (2023). Optimal liquidation of a basket of stocks using reinforcement learning. In 2023 Proceedings of the Conference on Control and its Applications (CT) (pp. 41-47). Society for Industrial and Applied Mathematics. https://doi.org/10.1137/1.9781611977745.6

[OK] Deep RL Portfolio Management (arXiv 2106.00123)

URL: https://arxiv.org/pdf/2106.00123

Key excerpts from Deep RL Portfolio Management (arXiv 2106.00123):

  • timeframe or cumulative wealth [7] or Sharpe ratio [8]. An issue that is usually problematic here

  • the portfolio log returns) is better as it normalizes the returns but still does not specifically

  • goal is to optimize the return on the investment of the capital exploiting the volatility of the

  • Convolutional Neural Networks - CNN [34] or Long Short Term Memory Networks - LSTM [35]),

  • Convergence Divergence (MACD) [25], Relative Strength Index (RSI) [26], Average Directional

  • DIAMOND: timeframe or cumulative wealth [7] or Sharpe ratio [8]. An issue that is usually problematic here

  • DIAMOND: the portfolio log returns) is better as it normalizes the returns but still does not specifically

  • DIAMOND: goal is to optimize the return on the investment of the capital exploiting the volatility of the

[FAILED] Hybrid ML Stock Prediction (MDPI Mathematics)

URL: https://www.mdpi.com/2227-7390/10/18/3302

[OK] Automated Trading System Survey (IEEE 9350582)

URL: https://ieeexplore.ieee.org/document/9350582

Key excerpts from Automated Trading System Survey (IEEE 9350582): (No extractable text)

[FAILED] Algorithmic Trading with ML Survey (ResearchGate)

URL: https://www.researchgate.net/publication/377990543_Algorithmic_trading_with_machine_learning_a_systematic_review

All Diamonds

  • 2.2.4 Mean Reversion ............................................................................................ 35
  • strategies. These types of funds merge mathematical and statistical models with
  • shifts past and above the double exponential moving average. Synchronously, he sets a
  • remain, ML creates valuable opportunities for ATS via alternative data sources, advanced feature engineering,
  • machine learning algorithms like neural networks, support vector machines, and random forests can be trained, and their
  • automated trading system, including components for order execution, risk management, and position sizing. This
  • – the unit price of property with the least favorable feature states.
  • – the unit price of a property with the most favorable feature states,
  • – one variables (“1” indicates the presence of a given feature state). We only have information that a
  • Fouque, J., Jaimungal, S., & Saporito, Y. F. (2022). Optimal Trading with Signals and Stochastic Price Impact. SIAM Journal on Financial Mathematics, 13(3), 944-968. https://doi.org/10.1137/21m1394473
  • Shafiq, S., Qureshi, S. S., & Akbar, M. (2023). Dynamic relationship of volatility of returns across different markets: evidence from selected next 11 countries. Journal of Economic and Administrative Sciences, (in press). https://doi.org/10.1108/jeas-09-2022-0216
  • Pemy, M., & Zhang, N. (2023). Optimal liquidation of a basket of stocks using reinforcement learning. In 2023 Proceedings of the Conference on Control and its Applications (CT) (pp. 41-47). Society for Industrial and Applied Mathematics. https://doi.org/10.1137/1.9781611977745.6
  • timeframe or cumulative wealth [7] or Sharpe ratio [8]. An issue that is usually problematic here
  • the portfolio log returns) is better as it normalizes the returns but still does not specifically
  • goal is to optimize the return on the investment of the capital exploiting the volatility of the