{"paper_id":"2508.16936","title":"THEME: Enhancing Thematic Investing with Semantic Stock Representations and Temporal Dynamics","authors":["Hoyoung Lee","Wonbin Ahn","Suhwan Park","Jaehoon Lee","Minjae Kim","Sungdong Yoo","Taeyoon Lim","Woohyung Lim","Yongjae Lee"],"paper_date":"2025-08-23","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2508.16936v2","page_url":"https://thequant.space/flowcharts/theme-enhancing-thematic-investing-with-semantic-stock-repr/","scores":{"empirical_rigor":6,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes THEME, a hierarchical contrastive learning framework that fine‑tunes stock embeddings using semantic and temporal supervision for thematic investing.","quote":"we introduce THEME, a framework that fine‑tunes embeddings using hierarchical contrastive learning.","summary":"Thematic investing, which aims to construct portfolios aligned with structural trends, remains a challenging endeavor due to overlapping sector boundaries and evolving market dynamics. A promising direction is to build semantic representations of investment themes from textual data. However…","strategy":"THEME (Ours)"},"assumptions":{"status":"available","items":[{"assumption":"Portfolios are constructed as equal‑weighted baskets of the top‑K retrieved stocks.","type":"execution","stated":"implied","quote":"For each window, we construct equal‑weighted portfolios using the"},{"assumption":"A 14‑day holding period is used to evaluate returns of retrieved stocks.","type":"execution","stated":"implied","quote":"stocks is then recorded over the subsequent 14 trading days."},{"assumption":"Two years of historical U.S. market data are sufficient for temporal refinement.","type":"data","stated":"implied","quote":"For the temporal refinement stage, we use two years of historical U.S. market data, generating training samples via a rolling window."},{"assumption":"Thematic ETFs with at least 10 constituents provide a reliable base for training.","type":"data","stated":"implied","quote":"We filter for ETFs with at least 10 constituents. The remaining 969 ETFs are randomly split into training (678), validation (97), and test (194) sets."}]},"datasets":{"status":"available","items":[{"name":"Thematic Representation Set (TRS)","provider":null,"kind":"text-news","access":"unknown","period":null,"universe":null,"quote":"we also construct the Thematic Representation Set (TRS)—a dataset that extends beyond real‑world ETF holdings by incorporating sectoral taxonomies and news‑derived themes."},{"name":"Real‑world thematic ETFs","provider":null,"kind":"benchmark","access":"unknown","period":null,"universe":"approximately 3,000 unique U.S. equities","quote":"The first component consists of 1,153 real‑world thematic ETFs covering approximately 3,000 unique U.S. equities."},{"name":"Two‑year historical U.S. market data","provider":null,"kind":"market-prices","access":"unknown","period":"two years","universe":null,"quote":"For the temporal refinement stage, we use two years of historical U.S. market data, generating training samples via a rolling window."}],"known":[],"sample":{"start":"2024-04","end":"2025-04","market":"US equities","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"THEME consistently improves portfolio quality over vanilla approaches, achieving higher Sharpe ratios and cumulative returns across top‑k cutoffs.","kind":"performance","quote":"As summarized in Table 2, THEME consistently improves portfolio quality over vanilla approaches."},{"finding":"THEME outperforms extensive baselines including strong LLM and embedding‑based baselines in retrieval precision and hit rate.","kind":"performance","quote":"In our experiments, THEME outperforms extensive baselines including strong LLM and embedding‑based baselines in retrieval precision and hit rate (Experiment 4.2)."}],"reported_performance":{"strategy":"THEME (Ours)","sharpe":0.7711,"sharpe_benchmark":0.4845,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":23.2},"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":20,"citations":{"cited_by_in_corpus":2,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":2},"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":"2026-11-14T17:29:14Z"},"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/"}