{"paper_id":"2407.05912","title":"Constructing an Investment Fund through Stock Clustering and Integer Programming","authors":["Maysam Khodayari Gharanchaei","Prabhu Prasad Panda"],"paper_date":"2024-04-27","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2407.05912v1","page_url":"https://thequant.space/flowcharts/constructing-an-investment-fund-through-stock-clustering-and/","scores":{"empirical_rigor":6,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes using integer programming combined with stock clustering to construct an index fund that tracks benchmark portfolios.","quote":"First of all, we used integer programming to formulate the stock clustering. This is a crucial step in constructing an index fund.","summary":"This paper focuses on the application of quantitative portfolio management by using integer programming and clustering techniques. Investors seek to gain the highest profits and lowest risk in capital markets. A data-oriented analysis of US stock universe is used to provide portfolio managers a…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The number of selected stocks k is substantially smaller than the total number of stocks n.","type":"model","stated":"explicit","quote":"The most common and practical approach is to choose 𝑘 stocks, where 𝑘 is substantially smaller than 𝑛."},{"assumption":"Weights of selected stocks are proportional to the total market capitalization of their clusters.","type":"model","stated":"explicit","quote":"The weights for the selected stocks will be proportionate to total market capitalization for the cluster represented by that stock normalized the market capitalization of the 81 stocks."},{"assumption":"Data are split into 65% training and 35% testing for model calibration.","type":"data","stated":"explicit","quote":"We split the data to 65% training and 35% testing. The training data set was used to calibrate the model."},{"assumption":"Rebalancing can be performed quarterly, semi‑annually, or annually.","type":"execution","stated":"explicit","quote":"We tried three rebalancing frequencies such as quarterly, semi annually, and annually."},{"assumption":"Daily returns are sufficient to calibrate the model.","type":"data","stated":"implied","quote":"For each stock, we computed the daily returns to calibrate our model."},{"assumption":"Market capitalization data from WRDS Compustat are accurate and representative.","type":"data","stated":"implied","quote":"In order to calculate the market capitalization, we downloaded the quarterly number of shares outstanding from ‘’WRDS Compustat’’."}]},"datasets":{"status":"available","items":[{"name":"NASDAQ 100 tickers","provider":"pytickersymbols package","kind":"benchmark","access":"public","period":null,"universe":"NASDAQ 100","quote":"We obtained the tickers for NASDAQ 100 through the ‘’pytickersymbols’’ package"},{"name":"Daily closing prices","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2014-2023","universe":"81 NASDAQ 100 stocks","quote":"then obtained daily closing prices of the tickers by using the Yahoo Finance package. The data collected ranges from 2014 to 2023.","known_id":"yahoo-finance"},{"name":"Quarterly shares outstanding","provider":"WRDS Compustat","kind":"fundamentals","access":"commercial","period":null,"universe":"81 NASDAQ 100 stocks","quote":"In order to calculate the market capitalization, we downloaded the quarterly number of shares outstanding from ‘’WRDS Compustat’’.","known_id":"compustat"}],"known":[{"id":"compustat","name":"Compustat","provider":"S&P Global","kind":"fundamentals","access":"commercial","quote":"In order to calculate the market capitalization, we downloaded the quarterly number of shares outstanding from ‘’WRDS Compustat’’.","mentions":1,"used_in":1},{"id":"wrds","name":"WRDS","provider":"Wharton Research Data Services","kind":"other","access":"commercial","quote":"In order to calculate the market capitalization, we downloaded the quarterly number of shares outstanding from ‘’WRDS Compustat’’.","mentions":1,"used_in":1},{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"We obtained the tickers for NASDAQ 100 through the ‘’pytickersymbols’’ package and then obtained daily closing prices of the tickers by using the Yahoo Finance package.","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":"no","headline_net_of_costs":null,"detail":null,"quote":"We measure our turnover (Qian, 2005) and tracking error for each approach","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"We measure our turnover (Qian, 2005) and tracking error for each approach","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Using a larger number of selected stocks (higher k) leads to lower tracking error and lower turnover across all benchmarks.","kind":"performance","quote":"We discovered that with a large value of k, we tend to get smaller tracking errors as well as turnover for all the benchmark values we tried out."},{"finding":"More frequent rebalancing (quarterly vs semi‑annual vs annual) generally reduces tracking error and turnover.","kind":"performance","quote":"We can also determine that rebalancing our portfolio more frequently generally leads to lower tracking error as well as turnover measure."},{"finding":"The optimization approach yields a much lower tracking error than the heuristic approach.","kind":"performance","quote":"Furthermore, the optimization approach yields a much lower tracking error since we have access to much more advanced tools than the heuristic approach."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[{"paper":{"paper_id":"2601.17021","title":"Regret-Driven Portfolios: LLM-Guided Smart Clustering for Optimal Allocation","paper_date":"2026-01-16","authors":["Muhammad Abro","Hassan Jaleel"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/regret-driven-portfolios-llm-guided-smart-clustering-for-optimal-allocation/"},"question":"Does quarterly rebalancing reduce tracking error and improve portfolio performance?","this_paper_finding":"More frequent rebalancing (quarterly vs semi‑annual vs annual) generally reduces tracking error and turnover.","other_paper_finding":"71% of configurations that outperformed SPY used a quarterly rebalancing schedule, indicating medium‑term rebalancing is beneficial.","other_paper_quote":"Among all the parameter configurations that outperformed SPY, 71% employed a quarterly rebalancing schedule.","note":"A shows quarterly rebalancing cuts tracking error and turnover; B shows 71% of out‑performing configs use quarterly rebalancing.","confidence":0.554}],"contradicts":[],"qualifies":[],"compared_with":12,"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":"2026-11-14T18:10:31Z"},"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/"}