{"paper_id":"2506.05764","title":"Exploring Microstructural Dynamics in Cryptocurrency Limit Order Books: Better Inputs Matter More Than Stacking Another Hidden Layer","authors":["Haochuan Wang"],"paper_date":"2025-06-06","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2506.05764v2","page_url":"https://thequant.space/flowcharts/exploring-microstructural-dynamics-in-cryptocurrency-limit-o/","scores":{"empirical_rigor":8.5,"math_complexity":5.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes that data preprocessing and hyperparameter tuning allow simpler models to match or exceed the performance of more complex neural networks, offering faster inference and greater interpretability.","quote":"Results reveal that, with data preprocessing and hyperparameter tuning, simpler models can match and even exceed the performance of more complex networks, offering faster inference and greater interpretability.","summary":"Cryptocurrency price dynamics are driven largely by microstructural supply demand imbalances in the limit order book (LOB), yet the highly noisy nature of LOB data complicates the signal extraction process. Prior research has demonstrated that deep-learning architectures can yield promising…","strategy":"XGBoost"},"assumptions":{"status":"available","items":[{"assumption":"All observable order‑book information is instantaneously incorporated into asset prices, leading to a 50:50 split in high‑frequency mid‑price moves.","type":"market","stated":"explicit","quote":"Under the Efficient Market Theorem, all observable order‑book information is instantaneously incorporated into asset prices, producing the empirically observed 50:50 split in high‑frequency mid‑price moves, and people will theoretically not be able to make profits, as the market has already incorporated past informatio"},{"assumption":"The latent state of each feature follows a simple random walk in the Kalman filter.","type":"model","stated":"explicit","quote":"The model assumes a simple random walk for the latent state, where Q and R denote the variances of the process and observation noise."},{"assumption":"The empirical analysis uses a single trading day of Bybit BTC/USDT LOB snapshots sampled at 100 ms intervals.","type":"data","stated":"explicit","quote":"All LOB data in this study were obtained from Bybit’s public historical data portal"},{"assumption":"Epsilon for ternary classification is tuned to achieve roughly equal class frequencies and inverse‑frequency weighting is applied in the loss.","type":"statistical","stated":"implied","quote":"we will tune ε to achieve roughly equal class frequencies when we do ternary split and apply inverse-frequency weighting in the loss so that rare “up” and “down” events incur proportionally greater penalty"},{"assumption":"Low latency is crucial for reducing slippage in high‑frequency trading.","type":"execution","stated":"implied","quote":"low latency—crucial for reducing slippage in high‑frequency trading."}]},"datasets":{"status":"available","items":[{"name":"Bybit BTC/USDT LOB snapshots","provider":"Bybit public historical data portal","kind":"order-book","access":"public","period":"2025-01-30","universe":"BTC/USDT","quote":"All LOB data in this study were obtained from Bybit’s public historical data portal","known_id":"bybit"}],"known":[{"id":"bybit","name":"Bybit","provider":"Bybit","kind":"market-prices","access":"public","quote":"3 Data Set All LOB data in this study were obtained from Bybit’s public historical data portal1.","mentions":5,"used_in":3},{"id":"fi-2010","name":"FI-2010","provider":"Ntakaris et al.","kind":"order-book","access":"public","quote":"Besides, many academic studies use preprocessed vendor datasets or lack a detailed walkthrough of the preprocessing process (FI-2010, B3).","mentions":2,"used_in":1}],"sample":{"start":null,"end":null,"market":"BTC/USDT","asset_class":"crypto","frequency":"intraday"},"data_resolution":"l2-book"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"Simpler models can match or exceed the performance of more complex networks when data preprocessing and hyperparameter tuning are applied.","kind":"performance","quote":"Results reveal that, with data preprocessing and hyperparameter tuning, simpler models can match and even exceed the performance of more complex networks, offering faster inference and greater interpretability."},{"finding":"Simpler models such as XGBoost and logistic regression marginally outperform the more complex neural networks by 1–2%.","kind":"performance","quote":"simpler models such as XGBoost and logistic regression marginally outperform our more complex neural networks by 1–2%."},{"finding":"Adding an extra CNN layer to a CNN + LSTM architecture did not yield the substantial accuracy gains expected.","kind":"negative","quote":"CNN + LSTM based architecture did not yield the substantial accuracy gains we expected"},{"finding":"All models consistently perform best after Savitzky–Golay smoothing, while Kalman filter results can be worse than raw data.","kind":"performance","quote":"all models consistently perform best after Savitzky–Golay smoothing. Note that the Kalman filter results are sometimes worse than using the raw data itself."},{"finding":"Binary and ternary prediction accuracy ranges from 0.42 to 0.71 across different prediction horizons and LOB depths.","kind":"predictive-accuracy","quote":"binary and ternary prediction accuracy ranges from 0.42 to 0.71—spanning 100ms predictions with 5-level LOB data to 1000ms predictions with 40-level LOB data."}],"reported_performance":{"strategy":"XGBoost","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":45,"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":"2026-11-14T17:36:31Z"},"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/"}