{"paper_id":"2510.14985","title":"DeepAries: Adaptive Rebalancing Interval Selection for Enhanced Portfolio Selection","authors":["Jinkyu Kim","Hyunjung Yi","Mogan Gim","Donghee Choi","Jaewoo Kang"],"paper_date":"2025-09-11","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.14985v1","page_url":"https://thequant.space/flowcharts/deeparies-adaptive-rebalancing-interval-selection-for-enhan/","scores":{"empirical_rigor":7,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes DeepAries, a novel deep reinforcement learning framework that jointly optimizes rebalancing timing and asset allocation.","quote":"We propose DeepAries , a novel deep reinforcement learning framework for dynamic portfolio management that jointly optimizes the timing and allocation of rebalancing decisions.","summary":"We propose DeepAries , a novel deep reinforcement learning framework for dynamic portfolio management that jointly optimizes the timing and allocation of rebalancing decisions. Unlike prior reinforcement learning methods that employ fixed rebalancing intervals regardless of market conditions…","strategy":"DeepAries"},"assumptions":{"status":"available","items":[{"assumption":"Fixed rebalancing intervals (e.g., daily or weekly) may be suboptimal.","type":"model","stated":"implied","quote":"Fixed rebalancing intervals (e.g., daily or weekly) may be suboptimal."},{"assumption":"Transaction costs are represented by a flat fee (e.g., 0.01%).","type":"execution","stated":"implied","quote":"the baseline transaction cost was set at 0.01%, and we subsequently examined fee scenarios with costs increased by 5-fold and 10-fold."}]},"datasets":{"status":"available","items":[{"name":"DJ 30, FTSE 100, KOSPI, CSI 300","provider":null,"kind":"market-prices","access":"public","period":"20 years","universe":null,"quote":"We extensively evaluate our method across four major markets: DJ 30 (U.S.), FTSE 100 (Europe), KOSPI (Korea), and CSI 300 (China) over 20 years."}],"known":[],"sample":{"start":null,"end":null,"market":"DJ 30, FTSE 100, KOSPI, CSI 300","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"baseline transaction cost set at 0.01% with additional scenarios at 5× and 10× the fee","quote":"the baseline transaction cost was set at 0.01%, and we subsequently examined fee scenarios with costs increased by 5-fold and 10-fold.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"baseline transaction cost set at 0.01% with additional scenarios at 5× and 10× the fee","card_quote":"the baseline transaction cost was set at 0.01%, and we subsequently examined fee scenarios with costs increased by 5-fold and 10-fold.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"DeepAries significantly outperforms traditional fixed-frequency and full-rebalancing strategies in risk-adjusted returns, transaction costs, and drawdowns.","kind":"performance","quote":"Extensive experiments on multiple real-world financial markets demonstrate that DeepAries significantly outperforms traditional fixed-frequency and full-rebalancing strategies in terms of risk-adjusted returns, transaction costs, and drawdowns."},{"finding":"Using iTransformer with adaptive rebalancing improves DJ 30 CAGR from 2.31% (Fixed) to 7.90% (Adaptive), Sharpe from 0.048 to 0.130, and reduces max drawdown from 21.81% to 13.67%.","kind":"performance","quote":"For instance, in the DJ 30 market, iTransformer achieves a CAGR improvement from 2.31% (Fixed) to 7.90% (Adaptive), with the Sharpe Ratio increasing from 0.048 to 0.130 and the Maximum Drawdown decreasing from 21.81% to 13.67%."},{"finding":"Adaptive rebalancing (DeepAries) is more resilient to higher transaction costs, yielding higher portfolio returns than a Fixed Daily baseline under 5× and 10× fee scenarios.","kind":"performance","quote":"In contrast, DeepAries’s adaptive rebalancing selection mitigates the negative impact of increased fees, resulting in relatively higher portfolio returns compared to the Fixed Daily baseline."}],"reported_performance":{"strategy":"DeepAries","sharpe":0.13,"sharpe_benchmark":null,"annual_return_pct":7.9,"total_return_pct":null,"max_drawdown_pct":13.67},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":20,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/dmis-lab/DeepAries","note":null},"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":"2026-11-14T17:27:28Z"},"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/"}