{"paper_id":"2410.04217","title":"Improving Portfolio Optimization Results with Bandit Networks","authors":["Gustavo de Freitas Fonseca","Lucas Coelho e Silva","Paulo André Lima de Castro"],"paper_date":"2024-10-05","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2410.04217v2","page_url":"https://thequant.space/flowcharts/improving-portfolio-optimization-results-with-bandit-network/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper introduces Adaptive Discounted Thompson Sampling (ADTS), Combinatorial Adaptive Discounted Thompson Sampling (CADTS), and a novel Bandit Networks architecture that integrates them for portfolio optimization.","quote":"We then extend this approach to the Portfolio Optimization problem by introducing the Combinatorial Adaptive Discounted Thompson Sampling (CADTS) algorithm","summary":"In Reinforcement Learning (RL), multi-armed Bandit (MAB) problems have found applications across diverse domains such as recommender systems, healthcare, and finance. Traditional MAB algorithms typically assume stationary reward distributions, which limits their effectiveness in real-world…","strategy":"Two Layer ADTS (n=4)"},"assumptions":{"status":"available","items":[{"assumption":"The experiments use historical daily returns of a fixed set of 44 S&P 500 stocks over a specific period, implying no intraday trading or slippage considerations.","type":"data","stated":"implied","quote":"using historical daily returns of 44 S&P 500 stocks from April 2020 to July 2024"}]},"datasets":{"status":"available","items":[{"name":"Historical daily returns of 44 S&P 500 stocks","provider":null,"kind":"market-prices","access":"unknown","period":"April 2020 to July 2024","universe":"44 S&P 500 stocks","quote":"using historical daily returns of 44 S&P 500 stocks from April 2020 to July 2024"}],"known":[],"sample":{"start":"2020-04","end":"2024-07","market":"44 S&P 500 stocks","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"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":"The best Bandit Network instance achieves an out-of-sample Sharpe Ratio 20% higher than the best classical model.","kind":"performance","quote":"The best network presenting an out-of-sample Sharpe Ratio 20% higher than the best performing classical model"},{"finding":"Two-Stage ADTS (n = 4) yields cumulative returns 168% higher than the CAPM, the best classical benchmark.","kind":"performance","quote":"cumulative returns of Two-Stage ADTS (n = 4) is 168% higher than the CAPM"},{"finding":"ADTS consistently achieves the lowest cumulative regret among the tested methods.","kind":"statistical","quote":"ADTS algorithm demonstrated superior performance, consistently achieving the lowest cumulative regret"},{"finding":"Two-Stage ADTS (n = 15) shows the smallest drawdown metric (0.55) among network instances, indicating better risk diversification.","kind":"performance","quote":"by selecting fifteen stocks simultaneously, the instance diversifies risks, as suggested by the smallest drawdown metric of the bandit networks instances (0.55)"},{"finding":"All Bandit Network instances outperform classical portfolio models (CAPM, Equal Weights, Risk Parity, Markowitz) in terms of returns.","kind":"performance","quote":"all the bandits network instances present superior performance. In this aspect, the cumulative returns of Two-Stage ADTS (n = 4) is 168% higher than the CAPM, where the last is the best-performing classical model"}],"reported_performance":{"strategy":"Two Layer ADTS (n=4)","sharpe":1.59,"sharpe_benchmark":1.32,"annual_return_pct":null,"total_return_pct":4.92,"max_drawdown_pct":0.9},"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":26,"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":"2026-11-14T17:59:49Z"},"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/"}