{"paper_id":"2611.22277","title":"Explaining Realized Returns: Roll's $R^2$ 40 Years Later","authors":["Bryan Kelly","Yinan Su","Chao Zhang"],"paper_date":"2026-11-17","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2611.22277","page_url":"https://thequant.space/flowcharts/explaining-realized-returns-rolls-r-2-40-years-later/","scores":{"empirical_rigor":8,"math_complexity":5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes extracting reasons from Wall Street Journal market commentary using generative AI and using these news‑based reasons to explain a substantial share of daily and monthly U.S. equity return variation.","quote":"These reasons explain around 30-40% of daily and monthly return variation out of sample.","summary":"Can we explain asset price movements even with hindsight? Reinterpreting Roll's (1988) AFA Presidential Address, \"R²,\" as a modern empirical exercise, we show that conventional macroeconomic, cash-flow, expectations, and flow variables explain less than 10% (often with negative R²) of monthly U.S.…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Explanatory variables must be observed independently of asset returns (criterion 1).","type":"data","stated":"explicit","quote":"Both components are therefore derived from concurrent return data and do not satisfy criterion 1.","support":"full"},{"assumption":"All non‑news baseline series are observed at monthly or lower frequency, limiting their explanatory power at higher frequencies.","type":"data","stated":"explicit","quote":"All non-news explanations considered in this paper are observed at monthly or lower frequency, whereas news can be used at the daily frequency.","support":"full"},{"assumption":"Quarterly macro, cash‑flow, expectations, and flow data can be transformed to monthly frequency by linear interpolation.","type":"data","stated":"explicit","quote":"In particular, the following simple example illustrates the linear transformation: YMar = Y (4Q) Q1 , YApr = 2 3 Y (4Q) Q1 + 1 3 Y (4Q) Q2 , YMay = 1 3 Y (4Q) Q1 + 2 3 Y (4Q) Q2 , YJun = Y (4Q) Q2 . Macro statistics.","support":"full"},{"assumption":"The out‑of‑sample R² is evaluated via five‑fold cross‑validation with strict hold‑out folds.","type":"statistical","stated":"explicit","quote":"We evaluate the explanatory power of the estimated relationship with out-of-sample R2 using a five-fold cross-validation split. Specifically, we split the sample period into five folds.","support":"full"},{"assumption":"Zero‑shot inference contains a persistence bias that can be removed by HAR filtering.","type":"model","stated":"explicit","quote":"Therefore, filtering does not introduce realized-return leakage: the filtered series remains consistent with Criterion 1 because it is not derived from asset returns. Filtering consistently improves R2 for both methods and at both frequencies, indicating both the prevalence of persistence bias and the effectiveness of HAR filtering in removing it.","support":"full"},{"assumption":"News‑based reasons are filtered to remove any leakage from realized returns.","type":"data","stated":"explicit","quote":"Therefore, filtering does not introduce realized-return leakage: the filtered series remains consistent with Criterion 1 because it is not derived from asset returns.","support":"full"}]},"datasets":{"status":"available","items":[{"name":"Wall Street Journal market‑summary reasons dataset","provider":"Wall Street Journal","kind":"text-news","access":"commercial","period":"2002–2024","universe":null,"quote":"We use generative AI to extract reasons stated in Wall Street Journal market summaries while filtering out price-related language. The full time series sample period is 2002–2024, aligned with our news-based reasons dataset.","support":"full"},{"name":"FRED‑MD macroeconomic statistics","provider":"FRED‑MD (McCracken & Ng, 2016)","kind":"macro","access":"public","period":null,"universe":null,"quote":"Macro Macroeconomic statistics: output, labor, etc., FRED-MD dataset excluding financial market indexes (McCracken and Ng, 2016) 99 Cash flow Dividends and earnings, aggregated at the S&P 500 level, from Shiller’s (2015) webpage 4 Subjective expectations Analyst forecasts of dividend and earnings, aggregated at the S&P 500 level (Delao and Myers, 2021) 4 Trading flows Net equity flows of various investor sectors,","support":"full","known_id":"fred"},{"name":"S&P 500 aggregate dividends and earnings","provider":"Robert Shiller website","kind":"fundamentals","access":"public","period":null,"universe":"S&P 500","quote":"Macro Macroeconomic statistics: output, labor, etc., FRED-MD dataset excluding financial market indexes (McCracken and Ng, 2016) 99 Cash flow Dividends and earnings, aggregated at the S&P 500 level, from Shiller’s (2015) webpage 4 Subjective expectations Analyst forecasts of dividend and earnings, aggregated at the S&P 500 level (Delao and Myers, 2021) 4 Trading flows Net equity flows of various investor sectors,","support":"full"},{"name":"Analyst forecasts of dividend and earnings (subjective expectations)","provider":"Delao & Myers (2021) via Sean Myers’ webpage","kind":"macro","access":"public","period":null,"universe":"S&P 500","quote":"Macro Macroeconomic statistics: output, labor, etc., FRED-MD dataset excluding financial market indexes (McCracken and Ng, 2016) 99 Cash flow Dividends and earnings, aggregated at the S&P 500 level, from Shiller’s (2015) webpage 4 Subjective expectations Analyst forecasts of dividend and earnings, aggregated at the S&P 500 level (Delao and Myers, 2021) 4 Trading flows Net equity flows of various investor sectors,","support":"full"},{"name":"Net equity flows by investor sector","provider":"Gabaix & Koijen (2021) methodology","kind":"alternative","access":"public","period":null,"universe":"12 investor sectors","quote":"Macro Macroeconomic statistics: output, labor, etc., FRED-MD dataset excluding financial market indexes (McCracken and Ng, 2016) 99 Cash flow Dividends and earnings, aggregated at the S&P 500 level, from Shiller’s (2015) webpage 4 Subjective expectations Analyst forecasts of dividend and earnings, aggregated at the S&P 500 level (Delao and Myers, 2021) 4 Trading flows Net equity flows of various investor sectors,","support":"full"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"Conventional macro, cash‑flow, expectations, and flow variables explain less than 10 % of monthly U.S. equity return variation out‑of‑sample, often yielding negative R².","kind":"predictive-accuracy","quote":"Reinterpreting Roll's (1988) AFA Presidential Address, \"$R^2$,\" as a modern empirical exercise, we show that conventional macroeconomic, cash-flow, expectations, and flow variables explain less than 10% (often with negative $R^2$) of monthly U.S. equity return variation out of sample and lack daily observations.","support":"full"},{"finding":"News‑based reasons explain roughly 30–40 % of daily and monthly return variation out‑of‑sample.","kind":"predictive-accuracy","quote":"These reasons explain around 30-40% of daily and monthly return variation out of sample.","support":"full"},{"finding":"Zero‑shot inference in raw form fails at the monthly frequency, but after filtering out temporal persistence it achieves an out‑of‑sample monthly R² of nearly 50 %.","kind":"predictive-accuracy","quote":"We also show that the zero-shot inference method fails when aggregated to the monthly frequency in its raw form, but can achieve a monthly out-of-sample R2 of nearly 50% with a simple adjustment that filters out the temporal persistence in the raw zero-shot predictions.","support":"full"},{"finding":"HAR filtering improves zero‑shot monthly R² from –115.03 % to 49.84 % and daily R² from 25.58 % to 31.88 %; embedding‑regression also improves after filtering.","kind":"predictive-accuracy","quote":"At the daily frequency, zero-shot R2 improves from 25.58% to 31.88%, exceeding the embedding-regression benchmark of 29.82%. The largest improvement is at the monthly frequency, where zero-shot R2 rises from −115.03% to 49.84% after filtering.","support":"full"},{"finding":"Flows have some explanatory power, but macro, cash‑flow, and expectations series show little robust explanatory power for market fluctuations.","kind":"statistical","quote":"12 tent with mechanisms in which flows have price impact or correlate with investor sentiment and other fundamental drivers of market movements (Shleifer and Summers, 1990; Gabaix and Koijen, 2021).11 The other three explanations (macroeconomic statistics, cash flow, and subjective expectations) do not have robust explanatory power for market fluctuations. These findings may simply reflect that the measured","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"cross-validation","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":20,"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":3,"extracted_at":"2026-11-18T11:39:14Z"},"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/"}