{"paper_id":"2504.20349","title":"ClusterLOB: Enhancing Trading Strategies by Clustering Orders in Limit Order Books","authors":["Yichi Zhang","Mihai Cucuringu","Alexander Y. Shestopaloff","Stefan Zohren"],"paper_date":"2025-04-29","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2504.20349v3","page_url":"https://thequant.space/flowcharts/clusterlob-enhancing-trading-strategies-by-clustering-order/","scores":{"empirical_rigor":6,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes ClusterLOB, a K-means++ based method that clusters market‑by‑order events using six time‑dependent features into three trader types to generate order‑flow imbalance signals for trading.","quote":"We introduce ClusterLOB as a method to cluster individual market events in a stream of market-by-order (MBO) data into different groups. To do so, each market event is augmented with six time-dependent features. By applying the K-means++ clustering algorithm to the resulting order features, we are then able to assign e","summary":"In the rapidly evolving world of financial markets, understanding the dynamics of limit order book (LOB) is crucial for unraveling market microstructure and participant behavior. We introduce ClusterLOB as a method to cluster individual market events in a stream of market-by-order (MBO) data into…","strategy":"Opportunistic cluster (ϕ2) trading strategy"},"assumptions":{"status":"available","items":[{"assumption":"The tick size on Nasdaq is $0.01 and is used as the price resolution for all orders.","type":"market","stated":"explicit","quote":"In this paper, we focus on the Nasdaq exchange, where the tick size π is $0.01."},{"assumption":"Three clusters (K=3) correspond to directional, opportunistic, and market‑making trader types.","type":"model","stated":"explicit","quote":"We set K = 3 as the number of clusters, which we retrospectively interpret as three trader types: directional, opportunistic, and market-making."},{"assumption":"Six time‑dependent features (V, Tm, T1, T′, SBS, OBS) capture the essential order‑flow characteristics.","type":"data","stated":"explicit","quote":"In the training dataset for each tick size groups, we create six time-dependent features for each stock, denoted as V , T m, T 1, T ′, SBS, and OBS, as described in Section 3.2.1.1"},{"assumption":"Cluster labels are made consistent across stocks by initializing K‑means++ with centroids from a reference stock.","type":"model","stated":"explicit","quote":"For all remaining stocks, initialize the K‑means++ clustering using the centroids obtained from Step 2 rather than using random initialization."},{"assumption":"Order‑flow imbalances are measured in 30‑minute buckets and used as trading signals.","type":"execution","stated":"explicit","quote":"order flow imbalances across different clusters within 30‑minute buckets, we extract alpha signals that provide actionable"},{"assumption":"Equal‑weighted PnL is rescaled to a target annualized volatility of 0.15 for risk‑adjusted comparison.","type":"statistical","stated":"explicit","quote":"Then, we rescale the equal‑weighted PnL by their volatility to target equal risk assignment, and set our annualized volatility target σtgt to be 0.15."}]},"datasets":{"status":"available","items":[{"name":"MBO data 2021","provider":"NASDAQ","kind":"order-book","access":"public","period":"2021","universe":"15 NASDAQ stocks (CHTR, GOOG, GS, IBM, MCD, NVDA, AAPL, ABBV, PM, CMCSA, CSCO, INTC, MSFT,","quote":"The small‑tick group comprises CHTR, GOOG, GS, IBM, MCD, and NVDA"}],"known":[{"id":"lobster","name":"LOBSTER","provider":"LOBSTER","kind":"order-book","access":"commercial","quote":"3.1 Data 3.1.1 Data description We gather our data through LOBSTER by Huang and Polak (2011), which uses ITCH data from NASDAQ to reproduce the LOB for any stock on NASDAQ to any specified level.","mentions":4,"used_in":1},{"id":"itch","name":"Nasdaq TotalView-ITCH","provider":"Nasdaq","kind":"order-book","access":"commercial","quote":"3.1 Data 3.1.1 Data description We gather our data through LOBSTER by Huang and Polak (2011), which uses ITCH data from NASDAQ to reproduce the LOB for any stock on NASDAQ to any specified level.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":"NASDAQ small‑tick stocks","asset_class":"equities","frequency":"intraday"},"data_resolution":"l2-book"},"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":"no","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The best clustering‑driven trading strategy outperforms benchmark strategies that do not use clustering, achieving higher Sharpe ratios.","kind":"performance","quote":"The results show that the best clustering‑driven trading strategy outperforms benchmark trading strategies, leading to improved trading performance and highlighting its predictive power."},{"finding":"Signals derived from cluster‑specific order‑flow imbalances consistently beat benchmarks across all event types (add, cancel, trade) for small‑, medium‑ and large‑tick stocks.","kind":"performance","quote":"Empirical results demonstrate that signals derived from clusters consistently outperform benchmark models without clustering in all event types, especially in terms of SR and other risk‑adjusted metrics."},{"finding":"Clustering reveals three distinct trader behaviors (directional, opportunistic, market‑making) that have interpretable correlations with price movements.","kind":"other","quote":"We classify market activity into three clusters: directional, opportunistic, and market‑making traders. These clusters reflect distinct behavioral patterns and interactions with the market microstructure"}],"reported_performance":{"strategy":"Opportunistic cluster (ϕ2) trading strategy","sharpe":1.34,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":7.1},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":26,"citations":{"cited_by_in_corpus":2,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"independent_papers":[{"paper":{"paper_id":"2610.16151","title":"Neural Estimation of Irreversibility in Real and Simulated Limit Order Book Paths","paper_date":"2026-10-12","authors":["Hyeonjun Yeo","Doohwi Cha","Yoontae Hwang"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/neural-estimation-of-irreversibility-in-real-and-simulated-limit-order-book/"},"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":true,"code_url":"https://github.com/YichiZhang-Oxford/ClusterLOB","note":null},"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":"2026-11-14T17:39:25Z"},"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/"}