{"paper_id":"2309.10546","title":"Mean Absolute Directional Loss as a New Loss Function for Machine Learning Problems in Algorithmic Investment Strategies","authors":["Jakub Michańków","Paweł Sakowski","Robert Ślepaczuk"],"paper_date":"2023-09-19","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2309.10546v1","page_url":"https://thequant.space/flowcharts/mean-absolute-directional-loss-as-a-new-loss-function-for-ma/","scores":{"empirical_rigor":6,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a new loss function called Mean Absolute Directional Loss (MADL) for optimizing machine learning models in algorithmic investment strategies.","quote":"We propose the Mean Absolute Directional Loss (MADL) function","summary":"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…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The study uses simple daily returns of the two assets as the basis for modeling.","type":"data","stated":"implied","quote":"We decided to use simple returns based on daily data of two assets from various asset classes: Bitcoin (BTC) and Crude Oil (represented by ETF named USO)."},{"assumption":"Minimizing the MADL loss will produce a profitable strategy when the loss value is negative and a loss when it is positive.","type":"model","stated":"implied","quote":"In our model, this function is minimized, ensuring that the strategy will produce a profit if it returns negative values and loss if it returns positive values."}]},"datasets":{"status":"available","items":[{"name":"Bitcoin (BTC) price data","provider":"Kraken, Bitfinex, BTC-e, CEX, Coinbase exchanges","kind":"market-prices","access":"public","period":"April 1, 2023 to December 31, 2021","universe":"Bitcoin","quote":"Source of the BTC data: Kraken, Bitfinex, BTC-e, CEX, and Coinbase exchanges","known_id":"coinbase"},{"name":"Crude Oil ETF (USO) price data","provider":"stooq.com","kind":"market-prices","access":"public","period":"April 1, 2023 to December 31, 2021","universe":"USO","quote":"USO data was obtained from stooq.com."}],"known":[{"id":"bitfinex","name":"Bitfinex","provider":"Bitfinex","kind":"market-prices","access":"public","quote":"Source of the BTC data: Kraken, Bitfinex, BTC-e, CEX, and Coinbase exchanges, while USO data was obtained from stooq.com. 8 4.","mentions":1,"used_in":1},{"id":"coinbase","name":"Coinbase","provider":"Coinbase","kind":"market-prices","access":"public","quote":"Source of the BTC data: Kraken, Bitfinex, BTC-e, CEX, and Coinbase exchanges, while USO data was obtained from stooq.com. 8 4.","mentions":1,"used_in":1},{"id":"kraken","name":"Kraken","provider":"Kraken","kind":"market-prices","access":"public","quote":"Source of the BTC data: Kraken, Bitfinex, BTC-e, CEX, and Coinbase exchanges, while USO data was obtained from stooq.com. 8 4.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Using the MADL loss function leads to better hyperparameter selection for the LSTM model and more efficient investment strategies.","kind":"performance","quote":"the new loss function enables us to select better hyperparameters for the LSTM model and obtain more efficient investment strategies"},{"finding":"The MADL/MADL approach consistently yields the highest risk‑adjusted return metrics among the tested loss‑function combinations.","kind":"performance","quote":"the result is always the best in s of MADL/MADL approach."},{"finding":"Regression results show that the MADL/MADL strategy has a significantly higher alpha (0.0029) and t‑stat (4.027) compared to other configurations.","kind":"statistical","quote":"MADL/MADL 0.0029 0.001 4.027 0.000"}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":21,"citations":{"cited_by_in_corpus":6,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":6},"independent_papers":[],"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":"2026-11-14T18:21:56Z"},"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/"}