{"paper_id":"2407.01818","title":"Predicting public market behavior from private equity deals","authors":["Paolo Barucca","Flaviano Morone"],"paper_date":"2024-07-01","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2407.01818v1","page_url":"https://thequant.space/flowcharts/predicting-public-market-behavior-from-private-equity-deals/","scores":{"empirical_rigor":6.5,"math_complexity":3,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a logit model that uses private equity transaction data to predict quarterly returns of the broad market and individual sectors.","quote":"We process private equity transactions to predict public market behavior with a logit model.","summary":"We process private equity transactions to predict public market behavior with a logit model. Specifically, we estimate our model to predict quarterly returns for both the broad market and for individual sectors. Our hypothesis is that private equity investments (in aggregate) carry predictive…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Private equity investors have access to confidential information that is not yet reflected in public markets.","type":"market","stated":"explicit","quote":"the key source of such predictive signal is the fact that, during their diligence process, private equity fund managers are privy to valuable company information that may not yet be reflected in the public markets at the time of their investment."},{"assumption":"Investors’ aggregate investment decisions reveal their informed opinion about near‑term public stock values.","type":"model","stated":"explicit","quote":"The investors’ market timing may reveal their aggregate, informed opinion about changes in the near‑term value of public stocks."},{"assumption":"Rational expectations hold, i.e., agents use all available information when making decisions.","type":"other","stated":"explicit","quote":"In the bigger picture, our hypothesis leverages the theory of rational expectations proposed by Muth in 1961"},{"assumption":"A rolling 7‑quarter estimation window provides sufficient data to re‑estimate the logit model each quarter.","type":"statistical","stated":"explicit","quote":"we use a rolling window approach, where the model is re‑estimated using a 7‑quarters period"},{"assumption":"The response variable can be defined as the sign of the forward return (or sector spread).","type":"model","stated":"explicit","quote":"we could have defined the response variable as the sign of the forward return, instead of the annualized forward return"},{"assumption":"The FactSet US Index and FactSet sector indices adequately represent broad market and sector behavior.","type":"data","stated":"explicit","quote":"we therefore elect to model both the systematic public market behavior (as represented by the FactSet US Index) and specific public market behavior (as represented by the 19 FactSet sector indices"}]},"datasets":{"status":"available","items":[{"name":"FactSet US Index","provider":"FactSet","kind":"market-prices","access":"commercial","period":"2000-01-01 to 2016-12-31","universe":"U.S. broad market index","quote":"model both the systematic public market behavior (as represented by the FactSet US Index)","known_id":"factset"},{"name":"FactSet sector indices","provider":"FactSet","kind":"market-prices","access":"commercial","period":"2000-01-01 to 2016-12-31","universe":"19 sector indices comprising the FactSet US Index","quote":"the 19 FactSet sector indices that comprise the FactSet US Index","known_id":"factset"},{"name":"Private equity deal data","provider":"FactSet","kind":"alternative","access":"commercial","period":"2000-01-01 to 2016-12-31","universe":"All significant PE deals in the U.S.","quote":"We have access to historical data on all significant PE deals","known_id":"factset"}],"known":[{"id":"factset","name":"FactSet","provider":"FactSet","kind":"fundamentals","access":"commercial","quote":"A. Data Extraction The first step consists in extracting private equity investment data from FactSet.","mentions":45,"used_in":5}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"weekly-monthly"},"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":"The logit model achieves predictive accuracy up to 70% in sectors such as Consumer Services, Communications, and Non Energy Minerals.","kind":"predictive-accuracy","quote":"showing a predictive accuracy of up to 70% in sectors such as Consumer Services, Communications, and Non Energy Minerals."},{"finding":"The model consistently outperforms a null model based on return statistics for both the broad market and sector forecasts.","kind":"performance","quote":"our model performs consistently better than a null model simply based on return statistics"},{"finding":"Average F1 score across sectors is 0.64, corroborating the forecasting performance evaluated from the ROC curve.","kind":"statistical","quote":"the average F1 score across sectors is equal to 0.64, thus corroborating the forecasting performance evaluated from the ROC curve."},{"finding":"ROC analysis shows the logit model provides superior classification of up‑ and down‑turns compared to the baseline.","kind":"performance","quote":"ROC curves are constructed by comparing the probabilistic predictions of the logit model"},{"finding":"A total of 50 out‑of‑sample quarterly predictions were generated for the broad market and each of the 19 sectors.","kind":"other","quote":"collecting a total of 50 predictions for the FactSet US Index and 50 predictions for each of the 19 market sectors"}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":22,"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":"2026-11-14T18:07:03Z"},"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/"}