{"paper_id":"2306.05568","title":"Maximally Machine-Learnable Portfolios","authors":["Philippe Goulet Coulombe","Maximilian Goebel"],"paper_date":"2023-06-08","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2306.05568v2","page_url":"https://thequant.space/flowcharts/maximally-machine-learnable-portfolios/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes MACE, a multivariate Alternating Conditional Expectations algorithm that jointly learns portfolio weights and a predictive function.","quote":"We introduce MACE, a multivariate extension of Alternating Conditional Expectations that achieves the aforementioned goal by wielding a Random Forest on one side of the equation, and a constrained Ridge Regression on the other.","summary":"When it comes to stock returns, any form of predictability can bolster risk-adjusted profitability. We develop a collaborative machine learning algorithm that optimizes portfolio weights so that the resulting synthetic security is maximally predictable. Precisely, we introduce MACE, a multivariate…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"An L2 regularization term guards against over‑fitting and unrealistic allocations.","type":"model","stated":"explicit","quote":"The addition of λ||w||2 provides l2 regularization with intensity λ (an hyperparameter) that will guard against overfitting and non‑realistic allocations"},{"assumption":"Time‑series dependence in predictors can bias out‑of‑bag predictions, requiring careful handling.","type":"statistical","stated":"implied","quote":"This persistence will break the non‑overfitting properties of OOB predictions – with an immediate consequence that f* s (Xt) includes overfitted elements"},{"assumption":"Transaction costs are proportional to portfolio turnover with a spread‑based multiplier.","type":"execution","stated":"explicit","quote":"We derive TC as some multiple of portfolio turnover, where we estimate the multiple (c) as one‑half the bid‑ask spread"}]},"datasets":{"status":"available","items":[{"name":"Welch and Goyal (2007) macro data set","provider":"Welch & Goyal","kind":"macro","access":"public","period":null,"universe":null,"quote":"utilizes the canonical Welch and Goyal (2007) data set to construct an MMLP with a subset of large‑cap individual stock returns from CRSP"},{"name":"CRSP large‑cap daily stock returns","provider":"CRSP","kind":"market-prices","access":"commercial","period":null,"universe":"large‑cap individual stocks","quote":"subset of large‑cap individual stock returns from CRSP","known_id":"crsp"},{"name":"Bid‑ask spreads of 100 stocks","provider":null,"kind":"market-prices","access":"unknown","period":"2017-01-01 to 2022-12-31","universe":"100 stocks","quote":"compute the distribution of c based on the bid‑ask spreads of all our 100 stocks, observed on a daily basis between 2017-01-01 and 2022-12-31"}],"known":[{"id":"crsp","name":"CRSP","provider":"Center for Research in Security Prices","kind":"market-prices","access":"commercial","quote":"The second application is at the monthly frequency and utilizes the canonical Welch and Goyal (2007) data set to construct an MMLP with a subset of large-cap individual stock returns from CRSP.","mentions":2,"used_in":2},{"id":"french-library","name":"Kenneth French Data Library","provider":"Kenneth R. French","kind":"market-prices","access":"public","quote":"We source the constituents of the five-factor model – market factor (MKT), size factor (SMB), value factor (HML), profitability (RMW), and investment factor (CMA) – from Kenneth R. French’s website.","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":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"partial","evidence_card":"yes","evidence_card_quoted":true},"conflict_kind":"graded","card_detail":"Three cost levels: 0.01%, 0.015%, 0.03% (50th, 75th, 90th percentile of bid‑ask spread).","card_quote":"take three candidates for c ∈{0.01%, 0.015%, 0.03%}, which correspond to the 50th, 75th, and 90th percentiles respectively","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"MACE achieves an out‑of‑sample R² above 4% in the last 15 years of the monthly sample, outperforming other RF‑based portfolios.","kind":"predictive-accuracy","quote":"MACE hits an R2 of above 4% in the last 15 years of our sample ending in 2019"},{"finding":"In the monthly exercise, MACE delivers an annualized average return of 18.70%, beating the next best model by six percentage points.","kind":"performance","quote":"The annualized average return of rA = 18.70% beats the closest competitor (EW (RF)) by a stunning six percentage points"},{"finding":"MACE attains a Sharpe Ratio of 1.05, higher than its variants and benchmarks, while keeping drawdowns low.","kind":"performance","quote":"both modified MACEs cannot keep up with the Sharpe Ratio of SR = 1.05"},{"finding":"Even with daily transaction costs up to 3 basis points, MACE remains highly competitive in absolute and risk‑adjusted returns.","kind":"performance","quote":"Even though we are trading at a daily frequency, MACE remains highly competitive, both in absolute, as well as risk‑adjusted returns"},{"finding":"During the Covid‑19 recession, MACE generates massive gains linked to unusually high R² values.","kind":"performance","quote":"MACEs generate massive gains during the short‑lived Pandemic recession. These can obviously be linked back to the abnormally high R2’s observed for that era"}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":33,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"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":"2026-11-14T18:26:08Z"},"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/"}