{"paper_id":"2412.15448","title":"Risk-Adjusted Performance of Random Forest Models in High-Frequency Trading","authors":["Akash Deep","Abootaleb Shirvani","Chris Monico","Svetlozar Rachev","Frank J. Fabozzi"],"paper_date":"2024-12-19","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2412.15448v2","page_url":"https://thequant.space/flowcharts/risk-adjusted-performance-of-random-forest-models-in-high-fr/","scores":{"empirical_rigor":6,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes integrating traditional technical indicators with random forest regression models for minute‑level high‑frequency stock price prediction.","quote":"This study evaluates the integration of traditional technical indicators with random forest regression models using minute-level SPY data","summary":"Because of the theoretical challenges posed by the Efficient Market Hypothesis to technical analysis, the effectiveness of technical indicators in high-frequency trading remains inadequately explored, particularly at the minute-level frequency, where effects of the microstructure of the market…","strategy":"Random Forest Regression (RFR) models with/without technical indicators"},"assumptions":{"status":"available","items":[{"assumption":"Trades are executed at minute‑end closing prices without accounting for bid‑ask spreads, commissions, or market impact.","type":"execution","stated":"implied","quote":"All trades are executed at minute-end closing prices. While this implementation provides realistic control of the sizes of the positions, it is somewhat optimistic, as it does not take into account bid–ask spreads, commission costs, or potential price impact."},{"assumption":"A per‑minute turnover constraint of 0.4% of portfolio value is imposed to reflect realistic liquidity limits.","type":"execution","stated":"explicit","quote":"To approximate real‑world trading constraints, we impose a turnover constraint limiting position changes in any minute to 0.4% of the portfolio value"},{"assumption":"The 10‑year US Treasury yield is used as a proxy for the risk‑free rate, converted to a per‑minute rate.","type":"data","stated":"explicit","quote":"The 10‑year US Treasury yield, provided on a daily basis, is used to compute a per‑minute risk‑free rate, which is necessary for calculating excess returns"},{"assumption":"Data are filtered to regular market hours (10:00 AM–3:30 PM CT) to avoid low‑liquidity periods.","type":"data","stated":"explicit","quote":"The dataset is filtered to focus on regular market trading hours, between 10:00 AM and 3:30 PM CT, to avoid periods of low liquidity"},{"assumption":"Training and testing splits are time‑ordered (80% train, 20% test) to prevent data leakage.","type":"data","stated":"explicit","quote":"The filtered dataset is then split into training and testing sets, with 80% of the data allocated to training and 20% to testing. The splitting is time‑ordered to preserve the temporal nature of the stock price data and avoid data leakage"},{"assumption":"Model performance is evaluated using risk‑adjusted metrics (Rachev, Sharpe, etc.) assuming returns are excess of the per‑minute risk‑free rate.","type":"statistical","stated":"implied","quote":"where rp is the asset return, rf is the risk‑free rate"}]},"datasets":{"status":"available","items":[{"name":"Minute‑level SPY data","provider":"Bloomberg Terminal","kind":"market-prices","access":"commercial","period":"April 2024 to September 2024","universe":"S&P 500 ETF (SPY)","quote":"The dataset used in this study consists of minute‑level historical stock data for the SPY (S&P 500 ETF), covering the period from April 2024 to September 2024","known_id":"bloomberg"},{"name":"10‑year US Treasury yield","provider":"Bloomberg Terminal","kind":"macro","access":"commercial","period":"April 2024 to September 2024","universe":null,"quote":"Additionally, the 10‑year US Treasury yield is incorporated as a proxy for the risk‑free rate, a crucial factor in calculating excess returns","known_id":"bloomberg"}],"known":[{"id":"bloomberg","name":"Bloomberg","provider":"Bloomberg L.P.","kind":"market-prices","access":"commercial","quote":"These data are reported daily and were also sourced from the Bloomberg Terminal, spanning the same time frame as the SPY data [Pastor and Stambaugh, 2003].","mentions":5,"used_in":2}],"sample":{"start":"2024-08","end":"2024-10","market":"SPY (S&P 500 ETF)","asset_class":"equities","frequency":"intraday"},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":"it does not take into account bid–ask spreads, commission costs, or potential price impact","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"it does not take into account bid–ask spreads, commission costs, or potential price impact","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"In‑sample R² values range from 0.749 to 0.812, but out‑of‑sample R² becomes negative, indicating severe over‑fitting.","kind":"predictive-accuracy","quote":"Our empirical results reveal a stark contrast between in‑sample and out‑of‑sample performance, with $R^2$ values deteriorating from 0.749--0.812 during training to negative values in testing"},{"finding":"Indicator‑enhanced models achieve Rachev ratios between 0.919 and 0.961 but generate negative returns (‑2.4% to ‑3.9%), underperforming a simple buy‑and‑hold benchmark.","kind":"performance","quote":"Although the indicator‑enhanced models achieved superior risk‑adjusted metrics, with Rachev ratios between 0.919 and 0.961, they consistently underperformed a simple buy‑and‑hold strategy, generating returns ranging from -2.4% to -3.9%"},{"finding":"Primary price‑based features account for over 60% of feature importance, while technical indicators contribute only 14%–15%.","kind":"statistical","quote":"A feature importance analysis demonstrates that primary price‑based features dominate the predictions made by the model, accounting for over 60% of the importance, while established technical indicators, such as RSI and Bollinger Bands, account for only 14%--15%"},{"finding":"Sharpe ratios of the random‑forest strategies are near zero (0.00 to 0.0046), indicating negligible risk‑adjusted returns.","kind":"performance","quote":"with Sharpe ratios near 0.00 to 0.0046"},{"finding":"Most trading losses occur during periods of heightened market volatility, suggesting static models struggle to adapt to shifting regimes.","kind":"negative","quote":"most trading losses occurred during periods of heightened market volatility, suggesting that the models struggle to adapt dynamically to shifting volatility regimes"}],"reported_performance":{"strategy":"Random Forest Regression (RFR) models with/without technical indicators","sharpe":0.0046,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":-2.4,"max_drawdown_pct":4},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[{"paper":{"paper_id":"2601.14062","title":"Demystifying the trend of the healthcare index: Is historical price a key driver?","paper_date":"2026-01-20","authors":["Payel Sadhukhan","Samrat Gupta","Subhasis Ghosh","Tanujit Chakraborty"],"empirical_rigor":5,"page_url":"https://thequant.space/flowcharts/demystifying-the-trend-of-the-healthcare-index-is-historica/"},"question":"Do price‑based features provide predictive utility for the target variable?","this_paper_finding":"Primary price‑based features account for over 60% of feature importance, while technical indicators contribute only 14%–15%.","other_paper_finding":"Raw original price features provide moderate but inconsistent predictive utility compared to nowcasting features.","other_paper_quote":"In contrast, historical price movement exhibits negligible predictive association with the directional movement of the opening index, while raw index values offer moderate but inconsistent predictive utility.","note":"A finds price features account for >60% importance, B finds raw price offers moderate but inconsistent utility versus nowcasting features.","confidence":0.536}],"compared_with":37,"citations":{"cited_by_in_corpus":2,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":1},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/akashdeepo/ML_TI_RFR","note":null},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T16:36:54Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}