{"paper_id":"2412.12576","title":"Market-Neutral Strategies in Mid-Cap Portfolio Management: A Data-Driven Approach to Long-Short Equity","authors":["Saumya Kothari","Harsh Shah","Utkarsh Prajapati","Shrinjay Kaushik"],"paper_date":"2024-12-17","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2412.12576v1","page_url":"https://thequant.space/flowcharts/market-neutral-strategies-in-mid-cap-portfolio-management-a/","scores":{"empirical_rigor":6,"math_complexity":3.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a data‑driven market‑neutral long‑short equity strategy tailored for mid‑cap stocks, achieving high risk‑adjusted returns.","quote":"This research builds upon the long‑short equity approach (e.g., Michaud, 2018; Dimitriu, Alexander, 2002) customized for mid‑cap equities, providing steady risk‑adjusted returns yielding a significant Sharpe ratio of 2.132 in test data.","summary":"Mid-cap companies, generally valued between $2 billion and $10 billion, provide investors with a well-rounded opportunity between the fluctuation of small-cap stocks and the stability of large-cap stocks. This research builds upon the long-short equity approach (e.g., Michaud, 2018; Dimitriu…","strategy":"mid-cap market-neutral long-short equity"},"assumptions":{"status":"available","items":[{"assumption":"Risk‑aversion parameter is fixed at A = 2 in the optimization framework.","type":"model","stated":"explicit","quote":"The strategy shows significant sensitivity to the risk‑aversion parameter (A = 2) in the optimization framework. We have used this risk aversion parameter as one of our assumptions"},{"assumption":"Portfolio must satisfy a dollar‑neutral constraint (equal long and short exposure).","type":"execution","stated":"explicit","quote":"Optimized portfolio weights using the dollar‑neutral constraint."},{"assumption":"Data are point‑in‑time (PIT) compliant to avoid look‑ahead bias.","type":"data","stated":"explicit","quote":"Using data from 2013 to 2023, obtained from WRDS and following point‑in‑time (PIT) compliance"},{"assumption":"Back‑testing uses a rolling‑window approach to maintain chronological consistency and avoid data leakage.","type":"model","stated":"explicit","quote":"Our back‑testing methodology aimed to validate the strategy’s robustness while avoiding look‑ahead bias and overfitting."},{"assumption":"Outliers are treated via reciprocal transformation and winsorization to reduce noise.","type":"statistical","stated":"explicit","quote":"We applied the Z‑score method from Python’s Scipy library to all the numeric features in our dataset"},{"assumption":"Sentiment scores are computed on a -1 to 1 scale and used as an average sentiment field in the dataset.","type":"data","stated":"explicit","quote":"It computed a compound sentiment score for each headline, which measured the overall sentiment (either positive, negative, or neutral) on a scale from -1 to 1, with -1 denoting extremely negative sentiment, 1 extremely positive and 0 a neutral sentiment. This value was stored in the ’avg sentiment’ data field in the fi"}]},"datasets":{"status":"available","items":[{"name":"WRDS mid‑cap stock data","provider":"WRDS","kind":"fundamentals","access":"commercial","period":"2013‑2023","universe":"mid‑cap companies ($2B‑$10B)","quote":"Using data from 2013 to 2023, obtained from WRDS and following point‑in‑time (PIT) compliance","known_id":"wrds"},{"name":"CRSP daily stock file","provider":"CRSP","kind":"other","access":"commercial","period":null,"universe":null,"quote":"Finally, for merging data from the CRSP and Compustat dataset, we used the CRSP‑Compustat link table to map “permno”s to “gvkey”s.","known_id":"crsp"},{"name":"Compustat fundamentals","provider":"Compustat","kind":"fundamentals","access":"commercial","period":null,"universe":null,"quote":"Finally, for merging data from the CRSP and Compustat dataset, we used the CRSP‑Compustat link table to map “permno”s to “gvkey”s.","known_id":"compustat"},{"name":"CapitalIQ news sentiment data","provider":"CapitalIQ","kind":"other","access":"commercial","period":null,"universe":null,"quote":"stored in the ’avg sentiment’ data field in the final dataset."}],"known":[{"id":"compustat","name":"Compustat","provider":"S&P Global","kind":"fundamentals","access":"commercial","quote":"Finally, for merging data from the CRSP and Compustat dataset, we used the CRSP-Compustat link table to map “permno”s to “gvkey”s.","mentions":6,"used_in":4},{"id":"crsp","name":"CRSP","provider":"Center for Research in Security Prices","kind":"market-prices","access":"commercial","quote":"Finally, for merging data from the CRSP and Compustat dataset, we used the CRSP-Compustat link table to map “permno”s to “gvkey”s.","mentions":6,"used_in":4},{"id":"wrds","name":"WRDS","provider":"Wharton Research Data Services","kind":"other","access":"commercial","quote":"By leveraging data spanning from 2013 to 2023, sourced from WRDS and adhering to point-in-time (PIT) compliance, the methodology ensured transparency and repro- ducibility.","mentions":5,"used_in":4}],"sample":{"start":"2013","end":"2023","market":"mid-cap stocks","asset_class":"equities","frequency":null},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":false,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"no","evidence_card":"partial","evidence_card_quoted":true},"conflict_kind":"graded","card_detail":"Costs are discussed qualitatively and noted could lower the reported Sharpe ratio, but no quantitative model is incorporated in the headline results.","card_quote":"it may be a valid to make this assumption that more the transaction and trading costs increase the algorithm will perform with lower Sharpe ratio than calculated.","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"In‑sample Sharpe ratio of the model is 2.59681.","kind":"performance","quote":"In‑sample Sharpe ratio: 2.59681."},{"finding":"Out‑of‑sample validation Sharpe ratio for 2022 is 2.3914.","kind":"performance","quote":"Out‑of‑sample Sharpe ratio: 2.3914."},{"finding":"Out‑of‑sample test Sharpe ratio for 2023 is 2.13211, with dollar‑neutral portfolio.","kind":"performance","quote":"Out‑of‑sample Sharpe ratio: 2.13211."},{"finding":"Portfolio returns in 2023 outperform the S&P 500 benchmark.","kind":"performance","quote":"Demonstrated strategy’s real‑world applicability, with high returns compared to benchmarks like the S&P 500, as seen in Fig. 3."},{"finding":"Weights of individual stocks are typically in the range (‑0.006, +0.006), indicating high diversification.","kind":"other","quote":"An important observation to note is the weights given to every stock are primarily occurring in the range of (-0.006, +0.006)."}],"reported_performance":{"strategy":"mid-cap market-neutral long-short equity","sharpe":2.132,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","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":"2026-11-14T17:49:32Z"},"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/"}