{"paper_id":"2307.05522","title":"Deep Inception Networks: A General End-to-End Framework for Multi-asset Quantitative Strategies","authors":["Tom Liu","Stephen Roberts","Stefan Zohren"],"paper_date":"2023-07-07","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2307.05522v1","page_url":"https://thequant.space/flowcharts/deep-inception-networks-a-general-end-to-end-framework-for/","scores":{"empirical_rigor":8.5,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes Deep Inception Networks (DINs), a family of deep learning models for end‑to‑end systematic multi‑asset trading that directly output portfolio position sizes.","quote":"We introduce Deep Inception Networks (DINs), a family of Deep Learning models that provide a general framework for end-to-end systematic trading strategies.","summary":"We introduce Deep Inception Networks (DINs), a family of Deep Learning models that provide a general framework for end-to-end systematic trading strategies. DINs extract time series (TS) and cross sectional (CS) features directly from daily price returns. This removes the need for handcrafted…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The model is trained with zero turnover and correlation regularisation in validation (Kvalid = Cvalid = 0).","type":"model","stated":"explicit","quote":"In this project, we set Kvalid = Cvalid = 0."},{"assumption":"Higher transaction‑cost coefficient C reduces portfolio turnover.","type":"execution","stated":"explicit","quote":"Increasing C encourages the model to reduce portfolio turnover."},{"assumption":"Features are extracted directly from daily price returns.","type":"data","stated":"explicit","quote":"DINs extract time series (TS) and cross sectional (CS) features directly from daily price returns."},{"assumption":"A proportional transaction‑cost model is used for evaluating profitability.","type":"execution","stated":"explicit","quote":"This is profitable until 4.82 basis points (bps) costs under a proportional cost model."},{"assumption":"The training loss accounts for transaction costs and correlation to a long‑only benchmark.","type":"model","stated":"explicit","quote":"where Rp,t are volatility‑scaled portfolio returns adjusted for transaction costs."}]},"datasets":{"status":"available","items":[{"name":"Futures","provider":"Pinnacle","kind":"market-prices","access":"unknown","period":"2000-2022","universe":"50 cross‑asset futures contracts","quote":"over 2000-2022. We select 50 cross-asset contracts"},{"name":"Equities","provider":"Compustat","kind":"market-prices","access":"unknown","period":"2001-2022","universe":"EURO STOXX 50 (EUR50) 50 blue‑chip European stocks","quote":"EURO STOXX 50 (EUR50) comprises 50 blue‑chip European stocks from Compustat","known_id":"compustat"},{"name":"Cryptocurrencies","provider":"CoinMarketCap","kind":"crypto-onchain","access":"public","period":"2018-2023","universe":"8 spot rates, top 25 coins by market cap as of Jan 2019","quote":"top 25 coins by market capitalisation (MCAP) on CMC as of January 2019","known_id":"coinmarketcap"}],"known":[],"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":"Performance reported with a proportional cost model; results shown for cost coefficients C from 0 to 5 bps and a breakeven cost of 4.82 bps.","quote":"This is profitable until 4.82 basis points (bps) costs under a proportional cost model.","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Performance reported with a proportional cost model; results shown for cost coefficients C from 0 to 5 bps and a breakeven cost of 4.82 bps.","card_quote":"This is profitable until 4.82 basis points (bps) costs under a proportional cost model.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The best DIN variant (OrigCIM‑TFT) achieves a Sharpe ratio of 2.95 and a breakeven transaction‑cost of 4.82 bps on the futures dataset.","kind":"performance","quote":"The optimal DIN variant for this dataset is OrigCIM‑TFT with Sharpe = 2.95 and BRK = 4.82 bps."},{"finding":"DIN models outperform all traditional TS and CS benchmarks before and after transaction costs, delivering about a 10× Sharpe increase over an equal‑weight long‑only portfolio.","kind":"performance","quote":"Evaluating on cross‑asset futures data from 2005‑2022, DIN models (OrigCIM x TFT) outperform all benchmarks before and after transaction costs. In particular, there is a 10x increase in Sharpe ratio to 2.95, compared to an equal-weight Long‑only portfolio, prior to transaction costs."},{"finding":"DIN performance remains robust across a range of transaction‑cost coefficients up to 4 bps, with Sharpe declining gradually as costs increase.","kind":"performance","quote":"Exhibit 7: Strategy performance at different transaction cost coefficients C"},{"finding":"The TFT position sizer consistently outperforms the LSTM variant and the long‑only benchmark across all time periods, with correlation to long‑only staying low (±30%).","kind":"performance","quote":"The TFT‑variant outperforms both the LSTM‑variant and Long‑only benchmark in all time periods. The correlation to Long‑only for both DIN variants also remains stably low between ±30%."}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":25,"citations":{"cited_by_in_corpus":7,"by_independent_authors":5,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":4,"unclassified":2},"independent_papers":[{"paper":{"paper_id":"2405.15833","title":"DSPO: An End-to-End Framework for Direct Sorted Portfolio Construction","paper_date":"2024-05-24","authors":["Jianyuan Zhong","Zhijian Xu","Saizhuo Wang","Xiangyu Wen","Jian Guo","Qiang Xu"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/dspo-an-end-to-end-framework-for-direct-sorted-portfolio-co/"},"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":"2026-11-14T18:25:12Z"},"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/"}