{"paper_id":"2401.16920","title":"Sparse Portfolio Selection via Topological Data Analysis based Clustering","authors":["Anubha Goel","Damir Filipović","Puneet Pasricha"],"paper_date":"2024-01-30","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2401.16920v2","page_url":"https://thequant.space/flowcharts/sparse-portfolio-selection-via-topological-data-analysis-bas/","scores":{"empirical_rigor":7.5,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes new time‑aware distance measures on persistence diagrams and landscapes and a TDA‑based clustering stock selection strategy for sparse portfolio construction.","quote":"We introduce new distance measures, which serve as an input to the clustering algorithm, on the space of persistence diagrams and landscapes that consider the time component of a time series.","summary":"This paper uses topological data analysis (TDA) tools and introduces a data-driven clustering-based stock selection strategy tailored for sparse portfolio construction. Our asset selection strategy exploits the topological features of stock price movements to select a subset of topologically…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The analysis uses daily closing prices of S&P 500 constituents.","type":"data","stated":"implied","quote":"We consider the daily closing prices of constituents of the S&P 500 index, obtained from the Thomson Reuters datastream spanning a period from 1st Dec 2009 to 31st August 2022."},{"assumption":"Portfolios are re‑balanced without explicit modeling of market impact or slippage.","type":"execution","stated":"implied","quote":"Fourth, we calculate the portfolio turnover ratio (TR) as a proxy for the transaction cost."}]},"datasets":{"status":"available","items":[{"name":"S&P 500 constituents daily closing prices","provider":"Thomson Reuters Datastream","kind":"market-prices","access":"commercial","period":"2009-12-01 to 2022-08-31","universe":"451 S&P 500 stocks","quote":"We consider the daily closing prices of constituents of the S&P 500 index, obtained from the Thomson Reuters datastream spanning a period from 1st Dec 2009 to 31st August 2022.","known_id":"refinitiv"}],"known":[{"id":"refinitiv","name":"Refinitiv / LSEG (Datastream, Eikon, Tick History)","provider":"LSEG","kind":"market-prices","access":"commercial","quote":"5.1 Data We consider the daily closing prices of constituents of the S&P 500 index, obtained from the Thomson Reuters datastream spanning a period from 1st Dec 2009 to 31st August 2022.15 The selection of the period stems from various reasons.","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":"partial","headline_net_of_costs":null,"detail":"Turnover ratio is used as a proxy for transaction costs; no explicit cost model is applied.","quote":"Fourth, we calculate the portfolio turnover ratio (TR) as a proxy for the transaction cost.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"partial","evidence_card_quoted":true},"card_detail":"Turnover ratio is used as a proxy for transaction costs; no explicit cost model is applied.","card_quote":"Fourth, we calculate the portfolio turnover ratio (TR) as a proxy for the transaction cost.","meaning":"costs appear only as a robustness check, a flat fee without spread or impact, or outside the headline numbers"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The sparse TDA‑based portfolio MV2 achieves the highest out‑of‑sample mean, Sharpe ratio and certainty‑equivalent return, and the lowest turnover, outperforming benchmark and other TDA portfolios.","kind":"performance","quote":"MV 2 achieves the maximum values for mean, SR, and CEQ, and the minimum value of TR, thus outperforming the other portfolios, including TDA‑based portfolios and the benchmark portfolios."},{"finding":"Cluster C2 delivers the highest information ratio and best trade‑off between excess return and tracking error among TDA‑based index‑tracking portfolios.","kind":"performance","quote":"C2 excels C4 as it attains the highest information ratio and maintains a trade‑off between the return over and above the benchmark index and the tracking error."},{"finding":"Affinity propagation clustering (APC) provides high correlation with the benchmark while keeping turnover low, balancing tracking accuracy and transaction costs.","kind":"performance","quote":"APC achieves this alignment without excessively high turnover, striking a balance between tracking the benchmark and maintaining low trading costs."},{"finding":"During the COVID‑19 volatile period, the sparse TDA‑based portfolio MV2 continues to outperform the benchmark, MV A, and the naive portfolio.","kind":"performance","quote":"the sparse TDA‑based portfolio MV 2 performs really well even in this highly volatile period"},{"finding":"All clustering‑based portfolios show less out‑of‑sample performance degradation than non‑clustering benchmarks, indicating robustness of the TDA filtering strategy.","kind":"performance","quote":"the difference between the in‑sample and out‑of‑sample average values is less than the MV A and GV A portfolios, which suggests that TDA‑based filtering strategy is more robust to the changing market dynamics."}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":23,"citations":{"cited_by_in_corpus":3,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":2},"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":"2026-11-14T18:15:33Z"},"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/"}