{"paper_id":"2306.02848","title":"HireVAE: An Online and Adaptive Factor Model Based on Hierarchical and Regime-Switch VAE","authors":["Zikai Wei","Anyi Rao","Bo Dai","Dahua Lin"],"paper_date":"2023-06-05","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2306.02848v1","page_url":"https://thequant.space/flowcharts/hirevae-an-online-and-adaptive-factor-model-based-on-hierar/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes HireVAE, the first deep learning based online and adaptive factor model with hierarchical latent space and regime-switching capability.","quote":"we propose the first deep learning based online and adaptive factor model, HireVAE, at the core of which is a hierarchical latent space that embeds the underlying relationship between the market situation and stock-wise latent factors","summary":"Factor model is a fundamental investment tool in quantitative investment, which can be empowered by deep learning to become more flexible and efficient in practical complicated investing situations. However, it is still an open question to build a factor model that can conduct stock prediction in…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The market score s is generated from a Gaussian market regime distribution.","type":"statistical","stated":"explicit","quote":"We assume that the market score s is a random variable generated from a market regime distribution defined as a Gaussian distribution."},{"assumption":"All training data must be point‑in‑time with no future information leakage.","type":"data","stated":"explicit","quote":"Practice requires an online learning setting that all data used for learning should be point-in-time data, meaning that there is no future information leakage at any timestamp in the training data set."},{"assumption":"The dataset consists of chronologically ordered samples D = {Dt0,…,Dtn}.","type":"data","stated":"explicit","quote":"In our setting, we have a set of samples labeled with time stamps sorted in chronological order: D = {Dt0, . . . , Dtn}"},{"assumption":"The market latent variable m0 follows a Gaussian distribution with parameters µm0 and σm0.","type":"model","stated":"explicit","quote":"where m0 ∈RHm follows a Gaussian distribution with parameters µm0 and σm0"},{"assumption":"The stock latent variable z0 follows a Gaussian distribution with parameters µs0 and σs0.","type":"model","stated":"explicit","quote":"z0 ∈RHs follows a Gaussian distribution with parameters µs0 and σs0"},{"assumption":"The hierarchical encoder‑decoder structure can capture market‑stock hierarchy and regime‑specific decoding.","type":"model","stated":"implied","quote":"we develop a hierarchical encoder with a two-level latent space representing a market‑stock hierarchy, and couple it with a set of regime‑specific decoders that reconstruct or predict stock returns based on different market situations"}]},"datasets":{"status":"available","items":[{"name":"China stock market","provider":"WIND database","kind":"market-prices","access":"commercial","period":"2010 to mid‑2022","universe":"all on‑listing Chinese stocks excluding ST and those listed <3 months","quote":"We conduct the experiment over the entire China stock market, with price‑volume and fundamental data obtained from the WIND database, and all raw data processed on a point‑in‑time basis.","known_id":"wind"}],"known":[{"id":"wind","name":"Wind","provider":"Wind Information","kind":"market-prices","access":"commercial","quote":"We conduct the experiment over the entire China stock market, with price-volume and fundamen-tal data obtained from the WIND database, and all raw data processed on a point-in-time basis.","mentions":1,"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":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"yes","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"HireVAE outperforms classical linear methods and recent non‑linear data‑driven methods by a large margin on real stock market data.","kind":"performance","quote":"Being the first online and adaptive regime‑switch factor model, HireVAE achieves superior performance on real stock market data, outperforming classical linear methods and recent non‑linear data‑driven methods by a large margin."},{"finding":"The adaptive regime‑switching algorithm consistently outperforms rule‑based and neural clustering baselines in stock prediction and portfolio construction.","kind":"performance","quote":"our adaptive regime switching algorithm can always outperform the rule‑based and neural clustering counterparts."},{"finding":"Adding market information does not significantly improve model performance.","kind":"negative","quote":"The results show that the additional market information does not help to improve the performance of a model."},{"finding":"A hierarchical latent space does not provide significant improvement over a single latent space when regime‑switching is not used.","kind":"negative","quote":"encoding market information alone does not provide significant improvement in the non‑regime‑swithcing modeling, since the metrics of VAE and HiVAE are similar."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":19,"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":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":"2026-11-14T18:26:12Z"},"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/"}