{"paper_id":"2312.03294","title":"A General Framework for Portfolio Construction Based on Generative Models of Asset Returns","authors":["Tuoyuan Cheng","Kan Chen"],"paper_date":"2023-12-06","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2312.03294v1","page_url":"https://thequant.space/flowcharts/a-general-framework-for-portfolio-construction-based-on-gene/","scores":{"empirical_rigor":7,"math_complexity":8,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes an integrated, high‑performance computing framework for constructing and optimizing cryptocurrency portfolios using generative‑model forecasts, objective functions, and a multi‑armed bandit‑based blending of strategies.","quote":"We present an integrated approach to portfolio construction and optimization, leveraging high-performance computing capabilities.","summary":"In this paper, we present an integrated approach to portfolio construction and optimization, leveraging high-performance computing capabilities. We first explore diverse pairings of generative model forecasts and objective functions used for portfolio optimization, which are evaluated using…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Rebalancing is performed every two days.","type":"execution","stated":"explicit","quote":"Rebalancing occurs every two days, targeting diverse combinations of generative dependence model forecasts and proxy objective functions."},{"assumption":"A flat transaction cost of 50 basis points per trade is applied.","type":"execution","stated":"explicit","quote":"The transaction cost c is set as 50 bps, together with the number of assets D = 12 and the constraint boundary multiplier m = 5."},{"assumption":"A rolling window of 91 steps (182 days) is used to fit generative models.","type":"model","stated":"explicit","quote":"To fit the generative model, we employ a rolling window length of 91 steps or 182 days."},{"assumption":"Historical price series from Binance and Coinbase are representative of cryptocurrency markets.","type":"data","stated":"implied","quote":"We retrieved price time series from Binance, spanning from 2018-06-10 to 2023-06-04, covering 12 currencies"},{"assumption":"The Kelly‑type objective function assumes a constant transaction cost aversion coefficient v.","type":"model","stated":"explicit","quote":"c denotes the constant transaction, and v is a transaction cost aversion coefficient, which is used to control portfolio turnover."},{"assumption":"Asset return dependence can be captured by vine‑copula or other generative models fitted by maximum likelihood.","type":"model","stated":"explicit","quote":"The regular vine copula structure is constructed by picking the maximum spanning tree, which maximizes the sum of absolute values of Kendall’s τ among pairwise variables while adhering to proximity conditions."}]},"datasets":{"status":"available","items":[{"name":"Binance cryptocurrency price series","provider":"Binance","kind":"market-prices","access":"public","period":"2018-06-10 to 2023-06-04","universe":"ADA, BNB, BTC, EOS, ETH, IOTA, LTC, NEO, ONT, QTUM, XLM, XRP (12 currencies priced in USDT","quote":"We retrieved price time series from Binance, spanning from 2018-06-10 to 2023-06-04, covering 12 currencies priced in USDT including ADA, BNB, BTC, EOS, ETH, IOTA, LTC, NEO, ONT, QTUM, XLM, and XRP.","known_id":"binance"},{"name":"Coinbase cryptocurrency price series","provider":"Coinbase","kind":"market-prices","access":"public","period":"2019-08-08 to 2023-08-17","universe":"BCH, BTC, EOS, ETC, ETH, LINK, LTC, XLM, XTZ, ZRX (10 currencies priced in USD)","quote":"spanning from 2019-08-08 to 2023-08-17, covering 10 currencies priced in USD including BCH, BTC, EOS, ETC, ETH, LINK, LTC, XLM, XTZ, and ZRX.","known_id":"coinbase"}],"known":[{"id":"coinbase","name":"Coinbase","provider":"Coinbase","kind":"market-prices","access":"public","quote":"Backtest To backtest eclectic portfolios, we retrieved price time series from Coinbase (we use a different exchange for this backtest, just to be sure our results are not sensitive to the data sources), spanning from 2019-08-08 to 2023-08-17, covering 10 currencies priced in USD including BCH, BTC, EOS, ETC, ETH, LINK, LTC, XLM, XTZ, and ZRX. As depicted in fig.","mentions":2,"used_in":2},{"id":"binance","name":"Binance","provider":"Binance","kind":"market-prices","access":"public","quote":"Backtest To backtest generative model-based portfolios, we retrieved price time series from Binance, spanning from 2018-06-10 to 2023-06-04, covering 12 curren-cies priced in USDT including ADA, BNB, BTC, EOS, ETH, IOTA, LTC, NEO, ONT, QTUM, XLM, and XRP. As depicted in fig.","mentions":2,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"A flat cost of 50 basis points per trade is incorporated in all backtests.","quote":"The transaction cost c is set as 50 bps, together with the number of assets D = 12 and the constraint boundary multiplier m = 5.","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"A flat cost of 50 basis points per trade is incorporated in all backtests.","card_quote":"The transaction cost c is set as 50 bps, together with the number of assets D = 12 and the constraint boundary multiplier m = 5.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Portfolios built with the vine‑copula generative model and Sharpe‑ratio objective consistently outperformed benchmarks and other model‑objective pairings.","kind":"performance","quote":"The Sharpe ratio portfolios, as classical finite‑moments portfolios, outperformed Kelly’s portfolios, quantile portfolios, and parity portfolios."},{"finding":"The vine copula emerged as the superior choice for multivariate dependence modeling across all experiments.","kind":"performance","quote":"Notably, the vine copula emerged as a superior choice for multivariate dependence modeling, and Sharpe ratio portfolios consistently outperformed alternative approaches."},{"finding":"Eclectic portfolios using cosine similarity and logit optimality delivered robust superior performance, surpassing individual generative‑model portfolios.","kind":"performance","quote":"We show that the value model utilizing cosine similarity and logit optimality consistently delivers robust superior performances."},{"finding":"Switching (greedy) eclectic portfolios exhibited higher variability but achieved higher average performance than blending (probability‑matching) portfolios.","kind":"performance","quote":"Switching portfolios exhibited higher variability but also achieved superior average performance compared to blending portfolios."},{"finding":"A moderate transaction‑cost aversion coefficient (v around 2–3) improves terminal profits, whereas too high a cost barrier limits returns.","kind":"performance","quote":"A moderate transaction cost aversion coefficient v around 2 to 3 is favorable, but too high a hurdle for trading could limit terminal profits."}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":18,"citations":{"cited_by_in_corpus":2,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":0},"independent_papers":[{"paper":{"paper_id":"2412.03038","title":"MILLION: A General Multi-Objective Framework with Controllable Risk for Portfolio Management","paper_date":"2024-12-04","authors":["Liwei Deng","Tianfu Wang","Yan Zhao","Kai Zheng"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/million-a-general-multi-objective-framework-with-controllab/"},"how":"uses_method_or_data","quote":null}],"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":"2026-11-14T18:18:22Z"},"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/"}