{"paper_id":"2504.13521","title":"Deep Learning Models Meet Financial Data Modalities","authors":["Kasymkhan Khubiev","Mikhail Semenov"],"paper_date":"2025-04-18","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2504.13521v2","page_url":"https://thequant.space/flowcharts/deep-learning-models-meet-financial-data-modalities/","scores":{"empirical_rigor":8,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes novel embedding techniques for limit order book data and a high‑frequency trading strategy based on those embeddings.","quote":"We present a novel approach to incorporating limit order book analysis into algorithmic trading by developing embedding techniques and treating sequential limit order book snapshots as distinct input channels in an image‑based representation.","summary":"Algorithmic trading relies on extracting meaningful signals from diverse financial data sources, including candlestick charts, order statistics on put and canceled orders, traded volume data, limit order books, and news flow. While deep learning has demonstrated remarkable success in processing…","strategy":"CNN2LSTM trading strategy on BTCUSDT and ETHUSDT futures"},"assumptions":{"status":"available","items":[{"assumption":"Orders of the minimal size are assumed to be executed with certainty.","type":"execution","stated":"explicit","quote":"The main limitation is that we expect the order to be executed for sure because the order size is the minimum available"},{"assumption":"Ask and bid prices are scaled using min‑max normalization relative to the mid‑price.","type":"data","stated":"explicit","quote":"We implement asks and bids prices scaling regarding to a specific LOB mid‑price accordingly"},{"assumption":"A sliding window of 30 consecutive LOB snapshots is used for forecasting and trading decisions.","type":"model","stated":"explicit","quote":"To perform the AMM trading strategy, we use sliding window with a size of 30 aggregation method for stacked and merged LOB snapshots"},{"assumption":"Forecast horizon is set to 1 second for mid‑price prediction.","type":"model","stated":"explicit","quote":"Having a sequence of N 2‑dimensional snapshots at time t we predict the mid‑price value or trend direction for a time τ = t + ∆t, having ∆t equal to 1 second"}]},"datasets":{"status":"available","items":[{"name":"LOB snapshots of 11 base cryptocurrencies (BTC, ETH, etc.)","provider":null,"kind":"order-book","access":"public","period":null,"universe":"BTC, ETH and other crypto pairs from OKeX, Binance, Huobi, Kraken","quote":"For the research, the authors used dataset of 11 unique base cryptocurrencies including BTC and ETH and trading pairs from four cryptoexchanges: OKeX, Binance, Huobi, and Kraken"},{"name":"BTC LOB dataset on Kaggle","provider":"Kaggle","kind":"order-book","access":"public","period":null,"universe":"BTC/USDT","quote":"Data availability The used dataset is published and accessible on Kaggle platform: https://www.kaggle.com/datasets/kkhubiev/btc-lob/data","known_id":"kaggle"}],"known":[{"id":"binance","name":"Binance","provider":"Binance","kind":"market-prices","access":"public","quote":"We collected Bitcoin (BTC), Etherium (ETH), Solana (SOL), Cardano (ADA), Tron (TRX), Telegram Open Network (TON), Binance coin (BNB), DOGEcoin (DOGE), and GOATcoin (GOAT) perpetual futures limit order books snapshots from November 27, 2024 to November 29, 2024 from the cryptocurrency exchange ByBit to perform experiments.","mentions":3,"used_in":1}],"sample":{"start":null,"end":null,"market":"BTCUSDT and ETHUSDT futures","asset_class":"crypto","frequency":"intraday"},"data_resolution":"l2-book"},"transaction_costs":{"status":"available","modeled":"partial","headline_net_of_costs":null,"detail":"The strategy focuses on earning with negative fees and assumes AMM execution costs are close to zero.","quote":"strategy mainly focuses on earning with negative fees and having AMM execution costs close to zero.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"partial","evidence_card_quoted":true},"card_detail":"The strategy focuses on earning with negative fees and assumes AMM execution costs are close to zero.","card_quote":"strategy mainly focuses on earning with negative fees and having AMM execution costs close to zero.","meaning":"costs appear only as a robustness check, a flat fee without spread or impact, or outside the headline numbers"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The proposed LOB processing methodology achieves state‑of‑the‑art performance in high‑frequency trading algorithms.","kind":"performance","quote":"Our methodology for processing limit order book data achieves state‑of‑the‑art performance in high‑frequency trading algorithms"},{"finding":"Using a one‑shot setting that stacks LOB snapshots of two assets reduces MAPE by roughly a factor of four for short horizons.","kind":"predictive-accuracy","quote":"The one‑shot setting helps to significantly reduce the error value approximately make it 4 times less in comparison with the single setting in case of the 0.2s and 1s forecasting horizons"},{"finding":"The CNN2LSTM‑based trading strategy on BTC and ETH futures shows strong performance with a positive spread and sufficient volume to profit from negative fees.","kind":"performance","quote":"The strategy demonstrates strong performance, having spread earning slightly positive, while generating sufficient trading volume to earn on negative fees"},{"finding":"A SimpleCNN 2D model with merged LOBs and price‑delta regression performed poorly, yielding low trading volume and a tendency to hold long positions.","kind":"negative","quote":"The SimpleCNN 2D with merged LOBs and price delta regression task had poor performance. The model tended to repeat the price trend, it had low trading volume and tendency to hold long position"}],"reported_performance":{"strategy":"CNN2LSTM trading strategy on BTCUSDT and ETHUSDT futures","sharpe":7.89,"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":29,"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":"2026-11-14T17:40:37Z"},"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/"}