{"paper_id":"2504.10914","title":"Breaking the Trend: How to Avoid Cherry-Picked Signals","authors":["Sebastien Valeyre"],"paper_date":"2025-04-15","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2504.10914v11","page_url":"https://thequant.space/flowcharts/breaking-the-trend-how-to-avoid-cherry-picked-signals/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes to empirically validate the theoretical Sharpe ratio model of a trend‑following strategy and shows that a single EMA indicator is optimal for capturing trends.","quote":"The main objective of this paper is to empirically validate the theoretical Sharpe ratio model proposed by Grebenkov and Serror (2014) and therefore their assumption to model trends as gaussian mean reversion stochastic processes with only one time scale.","summary":"Our empirical results show an impressive fit with the pretty complex theoretical Sharpe formula of a trend-following strategy depending on the parameter of the signal, which was derived by by Grebenkov and Serror (2014). That empirical fit convinces us that a mean-reversion process with only one…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Trends follow a Gaussian mean‑reversion process modeled as an AR(1) with a single time scale.","type":"model","stated":"explicit","quote":"The AR(1) process is characterized by one time scale parameter—indicating the average time needed to revert to zero—and a standard deviation that determines the level of noise."},{"assumption":"Portfolio smoothing with ρ = 1/20 reduces trading costs.","type":"execution","stated":"explicit","quote":"We then used the parameter ρ = 1/20 for portfolio smoothing as specified in Eq. (9) which is an very easy solution to reduce trading cost"},{"assumption":"Target‑volatility rescaling yields homoscedastic returns for Sharpe calculation.","type":"model","stated":"explicit","quote":"Finally, we applied a resizing process in Eq. (10) to target a constant volatility for the final positions ARP"}]},"datasets":{"status":"available","items":[{"name":"70 futures daily returns","provider":null,"kind":"market-prices","access":"unknown","period":"29 May 1990 – 7 Dec 2023","universe":"futures instruments in stock indices, bonds, FX and commodities","quote":"The simulation starts on the 29th of May 1990 and stops on the 7th of December 2023. We used daily returns from 70 futures instruments in stock indices, bonds, FX and commodities futures."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_extracted","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"none","rule":"R0","candidates":{"front_matter":"unclear","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"the classifier was not confident"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The empirical Sharpe ratio closely replicates the theoretical Sharpe ratio predicted by Grebenkov and Serror (2014).","kind":"performance","quote":"the empirical Sharpe ratio closely replicates the theoretical Sharpe ratio predicted by Grebenkov and Serror (2014), whose main result shows that a single EMA indicator is already optimal."},{"finding":"Estimated parameters: λ = 1/180 (±17) and β0 = 0.12, with R² = 0.98.","kind":"statistical","quote":"... We also obtained a R2 = 0.98 which could be only an indication for formal goodness‑of‑fit test."},{"finding":"A single EMA with a half‑life of 112 business days (78 business days) is the optimal parameter for Sharpe maximization.","kind":"theoretical","quote":"The best fit is obtained using the theoretical model parameters λ = 1/180 and β0 = 0.12. As a consequence, the parameter of 112 business days (equivalent to a half‑life period of 78 business days) for simple EMA is the optimal parameter to get the optimal Sharpe ratio."},{"finding":"Using a basket of more complex indicators does not improve Sharpe compared to the single EMA.","kind":"negative","quote":"we attempt to replicate the performance of a simple EMA using a basket of more complex trend indicators"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":32,"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":"2026-11-14T17:40:53Z"},"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/"}