{"paper_id":"2601.00593","title":"Uncertainty-Adjusted Sorting for Asset Pricing with Machine Learning","authors":["Yan Liu","Ye Luo","Zigan Wang","Xiaowei Zhang"],"paper_date":"2026-01-02","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2601.00593v1","page_url":"https://thequant.space/flowcharts/uncertainty-adjusted-sorting-for-asset-pricing-with-machine/","scores":{"empirical_rigor":9,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes sorting assets using uncertainty‑adjusted prediction bounds instead of point predictions alone.","quote":"We propose a simple change: sort assets using uncertainty‑adjusted prediction bounds instead of point predictions alone.","summary":"Machine learning is central to empirical asset pricing, but portfolio construction still relies on point predictions and largely ignores asset-specific estimation uncertainty. We propose a simple change: sort assets using uncertainty-adjusted prediction bounds instead of point predictions alone.…","strategy":"XGBoost long‑short portfolio"},"assumptions":{"status":"available","items":[{"assumption":"Exchangeability of observations for conformal prediction guarantees.","type":"statistical","stated":"explicit","quote":"Under an exchangeability assumption, these procedures deliver exact finite‑sample marginal coverage, regardless of the complexity of the underlying prediction algorithm."},{"assumption":"Predictive intervals are constructed without imposing parametric assumptions on the residual distribution.","type":"model","stated":"explicit","quote":"These bounds are obtained using rolling historical prediction residuals, without imposing parametric assumptions on the full residual distribution."},{"assumption":"Long‑short portfolios are formed by sorting stocks into deciles each month and weighting equally within each leg.","type":"execution","stated":"explicit","quote":"Each month, stocks are sorted into deciles based on predicted returns; the portfolio goes long the top decile and short the bottom decile, with equal weighting within each leg."},{"assumption":"Transaction costs are modeled as a proportional cost of 20 basis points per trade.","type":"execution","stated":"explicit","quote":"Following Avramov et al. (2023), we impose a proportional trading cost of 20 basis points per trade."},{"assumption":"The sample covers the full CRSP common‑stock universe from January 1967 to December 2016.","type":"data","stated":"explicit","quote":"The monthly sample covers January 1967 to December 2016 and includes the full CRSP common‑stock universe."}]},"datasets":{"status":"available","items":[{"name":"CRSP stock returns","provider":"CRSP","kind":"market-prices","access":"public","period":"1967–2016","universe":"U.S. common stocks","quote":"Stock returns CRSP Monthly 1967–2016 Compute next‑month excess returns using the 1M T‑bill rate.","known_id":"crsp"},{"name":"Firm characteristics","provider":"CRSP/Compustat","kind":"fundamentals","access":"public","period":"1967–2016","universe":"46 lagged firm characteristics","quote":"46 Firm characteristics CRSP/Compustat; CRSP Monthly / Annually 1967–2016 Annual variables updated at end of June; monthly variables updated at month‑end; cross‑sectional quantile transform each month.","known_id":"crsp"},{"name":"Macroeconomic variables","provider":"FRED‑MD","kind":"macro","access":"public","period":"1967–2016","universe":"178 macro variables","quote":"178 Macroeconomic variables FRED‑MD; medians of characteristics; Welch and Goyal (2008) Monthly 1967–2016 Apply standard transformations; expand to panel by assigning the same macro vector to all stocks each month.","known_id":"fred"}],"known":[],"sample":{"start":"1992","end":"2016","market":"US stocks","asset_class":"equities","frequency":"monthly"},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"A proportional cost of 20 basis points per trade is applied to all portfolio returns.","quote":"Following Avramov et al. (2023), we impose a proportional trading cost of 20 basis points per trade.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"A proportional cost of 20 basis points per trade is applied to all portfolio returns.","card_quote":"Following Avramov et al. (2023), we impose a proportional trading cost of 20 basis points per trade.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Uncertainty‑adjusted sorting yields portfolios that systematically outperform point‑prediction sorting in Sharpe ratio and volatility control.","kind":"performance","quote":"Empirically, the resulting portfolios systematically outperform their point‑prediction counterparts in terms of Sharpe ratios and volatility control."},{"finding":"Uncertainty‑adjusted portfolios reduce raw return spreads but substantially lower volatility, improving Sharpe ratios for most models.","kind":"performance","quote":"while uncertainty‑adjusted portfolio construction typically reduces raw return spreads relative to point‑prediction sorting, it substantially lowers portfolio volatility. As a result, uncertainty‑adjusted performance—as measured by Sharpe ratios and statistical significance—improves for the majority of models."},{"finding":"XGBoost point‑prediction long‑short portfolio delivers 39.45% annual return, 18.40% volatility, Sharpe 2.14; after 20 bps costs, return is 32.41% with Sharpe 1.76.","kind":"performance","quote":"The XGBoost long‑short portfolio delivers an annualized return of 39.45% with annualized volatility of 18.40%, corresponding to a Sharpe ratio of 2.14"},{"finding":"Elastic Net and PLS remain robust after transaction costs, maintaining Sharpe ratios around 1.29 and significant t‑statistics.","kind":"performance","quote":"Both models continue to deliver economically meaningful returns, with Sharpe ratios around 1.29 and Newey–West t‑statistic above 6."},{"finding":"Deeper neural‑network architectures (NN4, NN5) perform poorly and become marginal after transaction costs.","kind":"negative","quote":"deeper neural‑network architectures struggle to generate robust benchmark‑relative performance once trading frictions are introduced."}],"reported_performance":{"strategy":"XGBoost long‑short portfolio","sharpe":2.14,"sharpe_benchmark":null,"annual_return_pct":39.45,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":40,"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":"2026-11-14T17:17:26Z"},"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/"}