{"paper_id":"2404.01866","title":"Supervised Autoencoder MLP for Financial Time Series Forecasting","authors":["Bartosz Bieganowski","Robert Slepaczuk"],"paper_date":"2024-04-02","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2404.01866v2","page_url":"https://thequant.space/flowcharts/supervised-autoencoder-mlp-for-financial-time-series-forecas/","scores":{"empirical_rigor":8,"math_complexity":3.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes using supervised autoencoders with noise augmentation and triple barrier labeling to improve financial time series forecasting and strategy performance.","quote":"This paper investigates the enhancement of financial time series forecasting with the use of neural networks through supervised autoencoders, aiming to improve investment strategy performance. It specifically examines the impact of noise augmentation and triple barrier labeling on risk-adjusted returns","summary":"This paper investigates the enhancement of financial time series forecasting with the use of neural networks through supervised autoencoders, aiming to improve investment strategy performance. It specifically examines the impact of noise augmentation and triple barrier labeling on risk-adjusted…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Zero risk‑free rate is assumed for the Information Ratio calculation.","type":"model","stated":"explicit","quote":"Because we assume a zero-rate risk-free rate, instead of Sharpe Ration we will define IR"},{"assumption":"Stop‑losses and take‑profits from triple barrier labeling are executed immediately and perfectly.","type":"execution","stated":"explicit","quote":"The study also assumes that stop-losses and take profits from triple barrier labeling are executed immediately and perfectly"},{"assumption":"Historical price data are representative for evaluating future strategy performance.","type":"market","stated":"implied","quote":"the findings are based on historical data, and as such, their predictive power in relation to future performance should be considered with caution"},{"assumption":"Features must be stationary for supervised learning to be reliable.","type":"data","stated":"explicit","quote":"Supervised learning requires stationary features because it involves mapping an unseen observation to labeled examples to predict the observation’s label"},{"assumption":"Transaction costs are fixed percentages per trade side with no market impact.","type":"execution","stated":"explicit","quote":"Transaction cost for S&P 500 Index and EUR/USD amounts to 0.005%, for Bitcoin it is 0.1%"},{"assumption":"The model’s Gaussian noise augmentation is applied to features before training.","type":"model","stated":"explicit","quote":"Data augmentation has found a valuable place in the domain of time series analysis as well"}]},"datasets":{"status":"available","items":[{"name":"S&P 500 index daily prices","provider":"FirstRateData","kind":"market-prices","access":"public","period":"2010-01-01 to 2022-04-30","universe":"S&P 500 constituents","quote":"The study focuses on the S&P 500 index, EUR/USD, and BTC/USD as the traded assets from January 1, 2010, to April 30, 2022"},{"name":"EUR/USD daily prices","provider":"FirstRateData","kind":"market-prices","access":"public","period":"2010-01-01 to 2022-04-30","universe":"EUR/USD spot market","quote":"The study focuses on the S&P 500 index, EUR/USD, and BTC/USD as the traded assets from January 1, 2010, to April 30, 2022"},{"name":"BTC/USD daily prices","provider":"FirstRateData","kind":"market-prices","access":"public","period":"2010-01-01 to 2022-04-30","universe":"Bitcoin spot market","quote":"The study focuses on the S&P 500 index, EUR/USD, and BTC/USD as the traded assets from January 1, 2010, to April 30, 2022"},{"name":"Initial Claims (ICSA) series","provider":"Federal Reserve Bank of St. Louis (FRED)","kind":"macro","access":"public","period":null,"universe":null,"quote":"the first one is the seasonally adjusted Initial Claims (ICSA), retrieved from the Federal Reserve Bank of St. Louis, FRED","known_id":"fred"}],"known":[{"id":"fred","name":"FRED","provider":"Federal Reserve Bank of St. Louis","kind":"macro","access":"public","quote":"2.2 Feature Time Series When it comes to the time series used as features in this paper, the first one is the seasonally adjusted Initial Claims (ICSA), retrieved from the Federal Reserve Bank of St. Louis, FRED.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"Transaction cost for S&P 500 Index and EUR/USD amounts to 0.005%, for Bitcoin it is 0.1%","quote":"Transaction cost for S&P 500 Index and EUR/USD amounts to 0.005%, for Bitcoin it is 0.1%","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Transaction cost for S&P 500 Index and EUR/USD amounts to 0.005%, for Bitcoin it is 0.1%","card_quote":"Transaction cost for S&P 500 Index and EUR/USD amounts to 0.005%, for Bitcoin it is 0.1%","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Supervised autoencoders significantly improve strategy performance, with an optimal balance of Gaussian noise level and bottleneck size.","kind":"performance","quote":"Through rigorous testing and sensitivity analysis, we demonstrated that employing supervised autoencoders significantly enhanced the performance metrics of the strategy"},{"finding":"Excessive noise and overly large bottleneck sizes degrade performance, likely due to overfitting and added noise.","kind":"negative","quote":"an increase in the level of noise and bottleneck size beyond certain thresholds led to a decrease in performance"},{"finding":"Approach 3 (with noise augmentation and denoising autoencoder) outperformed Approaches 1 and 2 across all bar lengths in Information Ratio of an equally weighted portfolio.","kind":"performance","quote":"Approach 3 outperformed Approaches 1 and 2 across all bar lengths in terms of the Information Ratio of an equally weighted portfolio"},{"finding":"Triple barrier labeling generally outperforms simple direction classification, especially on 15‑minute and 30‑minute bars.","kind":"performance","quote":"Triple barrier labeling generally outperformed simple labeling due to its ability to handle market noise better"},{"finding":"In the 5‑minute bar setting, the equally‑weighted portfolio showed a marginal cumulative loss of -2.16% with an information ratio of -0.11.","kind":"performance","quote":"The equally-weighted portfolio, however, resulted in a marginal cumulative loss of -2.16%, an information ratio of -0.11"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":20,"citations":{"cited_by_in_corpus":3,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":2},"independent_papers":[{"paper":{"paper_id":"2508.19006","title":"Is attention truly all we need? An empirical study of asset pricing in pretrained RNN sparse and global attention models","paper_date":"2025-08-26","authors":["Shanyan Lai"],"empirical_rigor":9,"page_url":"https://thequant.space/flowcharts/is-attention-truly-all-we-need-an-empirical-study-of-asset/"},"how":"uses_method_or_data","quote":null}],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"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":"2026-11-14T18:11:59Z"},"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/"}