{"paper_id":"2510.15288","title":"Portfolio Optimization of Indonesian Banking Stocks Using Robust Optimization","authors":["Visca Tri Winarty","Sena Safarina"],"paper_date":"2025-10-17","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2510.15288v1","page_url":"https://thequant.space/flowcharts/portfolio-optimization-of-indonesian-banking-stocks-using-ro/","scores":{"empirical_rigor":6,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes constructing uncertainty sets with moving‑window and bootstrapping methods and applying robust optimization to Indonesian banking stocks, showing the moving‑window approach yields a better risk‑return trade‑off for risk‑tolerant investors.","quote":"This study constructs such sets using moving-window and bootstrapping methods and applies them to Indonesian banking stock data with varying risk‑aversion parameters. The results show that robust optimization with the moving-window method, particularly with a smaller risk‑aversion parameter, provides a better risk‑retu","summary":"Since the COVID-19 pandemic, the number of investors in the Indonesia Stock Exchange has steadily increased, emphasizing the importance of portfolio optimization in balancing risk and return. The classical mean-variance optimization model, while widely applied, depends on historical return and risk…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"No short selling is allowed (asset weights between 0 and 1).","type":"model","stated":"explicit","quote":"0 ≤xi ≤1 for i = 1, 2, . . . , n indicates no short selling in this classical model."},{"assumption":"Parameters µ and Σ are known with certainty in the classical model.","type":"model","stated":"explicit","quote":"The classical model (1) presumes that both parameters (2) and (3) are known with certainty."},{"assumption":"Risk‑aversion parameter γ is positive.","type":"model","stated":"explicit","quote":"In the objective function, γ ∈R++ represents the risk‑aversion parameter"},{"assumption":"A 90‑day moving window (K = 90) is used to capture recent market dynamics.","type":"data","stated":"explicit","quote":"we used 90‑day window length (K = 90), corresponding to quarterly financial reporting periods"}]},"datasets":{"status":"available","items":[{"name":"Indonesian banking stock data","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":"Indonesian banking stocks","quote":"applies them to Indonesian banking stock data with varying risk‑aversion parameters"}],"known":[],"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":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Robust optimization with moving‑window uncertainty sets yields lower objective values than bootstrapping, indicating a more favorable risk‑return trade‑off.","kind":"performance","quote":"γ, robust optimization with uncertainty sets derived from the moving‑window method consistently produces better results than those derived from the bootstrapping method, as shown by its smaller objective values."},{"finding":"Under both good and poor market conditions, the moving‑window method generated profits, while the bootstrapping method resulted in losses across all risk‑aversion levels.","kind":"performance","quote":"The moving‑window method yields profits of Rp. 735.00 for γ = 5, losses of Rp. 2,040.00 for γ = 50, and losses of Rp. 2,629.00 for γ = 100. On the other hand, the bootstrapping method results in losses across all cases Rp. 3,830.00 for γ = 5, Rp. 3,870.00 for γ = 20, and Rp. 3,830.00 for γ = 100."},{"finding":"Portfolio return graphs show the moving‑window method delivers higher profits for low risk‑aversion (γ = 5) while maintaining competitive performance for higher γ values.","kind":"performance","quote":"portfolio return graphs across different γ values show that the moving‑window method delivers higher profits when γ = 5, corresponding to risk‑taking investors, while still maintaining competitive performance under higher γ values."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":18,"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":"2026-11-14T17:24:21Z"},"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/"}