{"paper_id":"2411.14646","title":"Diversification quotient based on expectiles","authors":["Xia Han","Liyuan Lin","Hao Wang","Ruodu Wang"],"paper_date":"2024-11-22","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2411.14646v2","page_url":"https://thequant.space/flowcharts/diversification-quotient-based-on-expectiles/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a diversification quotient based on expectiles as an alternative to VaR and ES, with simple formulas and a connection to the Omega ratio.","quote":"We study DQ based on expectiles, offering a useful alternative to conventional risk measures such as Value-at-Risk (VaR) and Expected Shortfall (ES).","summary":"A diversification quotient (DQ) quantifies diversification in stochastic portfolio models based on a family of risk measures. We study DQ based on expectiles, offering a useful alternative to conventional risk measures such as Value-at-Risk (VaR) and Expected Shortfall (ES). The expectile-based DQ…","strategy":"Minimizing DQex α (expectile-based diversification quotient)"},"assumptions":{"status":"available","items":[{"assumption":"The level α is in (0, 1/2).","type":"statistical","stated":"explicit","quote":"For a given α ∈(0, 1/2), DQex α has the alternative formula"},{"assumption":"The loss vector X follows an elliptically distributed model.","type":"model","stated":"explicit","quote":"A random vector X is elliptically distributed if its characteristic function can be written as"},{"assumption":"Data are iid (or satisfy an ergodicity condition) for empirical estimation.","type":"data","stated":"explicit","quote":"Assume we have data X(1), . . . , X(N) sampled from X satisfying some ergodicity condition (being iid would be sufficient)."},{"assumption":"Portfolio weights sum to one and are non‑negative.","type":"execution","stated":"explicit","quote":"selecting portfolio weights w = (w1, . . . , wn) ∈∆n to minimize DQ based expectiles, where ∆n := {w ∈[0, 1]n : w1 + · · · + wn = 1} ."},{"assumption":"No transaction costs are incurred in the back‑test.","type":"execution","stated":"explicit","quote":"assuming no transaction costs."}]},"datasets":{"status":"available","items":[{"name":"S&P 500 sector portfolios (40 stocks)","provider":null,"kind":"market-prices","access":"unknown","period":"Jan 2014 to Dec 2023","universe":"40 stocks from S&P 500 sectors","quote":"We use data from January 2, 2014, to December 28, 2023 to build up the portfolio, with the risk‑free rate r = 2.13%"},{"name":"Synthetic equicorrelated normal data","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"An illustration of a portfolio vector from an equicorrelated normal distribution is …"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"The historical asset prices are from Yahoo Finance and we use the period from January 2, 2014, to December 29, 2023, with a total of 2516 observations of daily losses and 500 trading days for the initial training.","mentions":1,"used_in":1}],"sample":{"start":"2016-01","end":"2023-12","market":"40 US stocks","asset_class":"equities","frequency":"monthly"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":"assuming no transaction costs.","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"assuming no transaction costs.","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Minimizing the expectile‑based DQ yields the highest Sharpe ratio and lower volatility compared to strategies based on VaR, ES or maximizing the Omega ratio.","kind":"performance","quote":"We can see from Table 3 that the strategy based on minimizing DQex α , with the highest Sharp ratio, is quite competitive compared with other strategies. In particular, the annualized volatility for minimizing DQex α is relatively lower than that of maximizing the Omega ratio."},{"finding":"Expectile‑based DQ increases steadily with α, while VaR‑ and ES‑based DQ remain zero for small α due to scarce tail data.","kind":"statistical","quote":"When α is less than 0.1, both DQVaR α and DQES α are zero, and as α increases, they provide no further useful information. However, the expectile‑based DQ steadily increases with α for α ∈(0, 0.1)."},{"finding":"The expectile‑based DQ exhibits pseudo‑convexity, allowing efficient gradient‑descent optimization and linear programming solutions.","kind":"theoretical","quote":"The expectile‑based DQ exhibits pseudo‑convexity in portfolio weights, allowing gradient descent algorithms for portfolio selection. We show that the corresponding optimization problem can be efficiently solved using linear programming techniques in real‑data applications."}],"reported_performance":{"strategy":"Minimizing DQex α (expectile-based diversification quotient)","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":10.19,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":17,"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":"2026-11-14T17:52:44Z"},"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/"}