{"paper_id":"2309.16679","title":"Leveraging Deep Learning and Online Source Sentiment for Financial Portfolio Management","authors":["Paraskevi Nousi","Loukia Avramelou","Georgios Rodinos","Maria Tzelepi","Theodoros Manousis","Konstantinos Tsampazis","Kyriakos Stefanidis","Dimitris Spanos","Manos Kirtas","Pavlos Tosidis","Avraam Tsantekidis","Nikolaos Passalis","Anastasios Tefas"],"paper_date":"2023-07-23","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2309.16679v2","page_url":"https://thequant.space/flowcharts/leveraging-deep-learning-and-online-source-sentiment-for-fin/","scores":{"empirical_rigor":4,"math_complexity":7,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes adaptive data normalization methods, reward shaping policies, and the integration of sentiment information to improve deep learning based financial trading agents.","quote":"... the proposed reward shaping policy proved helpful in both cases compared to the baseline PnL and Fee rewards.","summary":"Financial portfolio management describes the task of distributing funds and conducting trading operations on a set of financial assets, such as stocks, index funds, foreign exchange or cryptocurrencies, aiming to maximize the profit while minimizing the loss incurred by said operations. Deep…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Commission fee c is set slightly higher than the actual commission to account for price slippage.","type":"execution","stated":"explicit","quote":"c is typically set to a value slightly higher than the actual commission paid to account for price slippage and possible risks."},{"assumption":"Financial time‑series measurements are generated from a Gaussian (or Gaussian mixture) distribution for normalization.","type":"statistical","stated":"explicit","quote":"Assuming a Gaussian distribution for each measurement vector"},{"assumption":"A threshold (pthres) is set high enough to overcome any commission fees and price slippage.","type":"execution","stated":"explicit","quote":"Typically, pthres is set to a value high enough to overcome any commission fees, as well as to account for price slippage that might occur."},{"assumption":"Agents can exit the market without terminating training and may re‑enter later.","type":"execution","stated":"explicit","quote":"Note that usually exiting the market does not terminate the training process and the agent has the opportunity to reenter in it."},{"assumption":"Sentiment extracted from online sources can be a stronger predictor than price alone for Bitcoin trading.","type":"other","stated":"explicit","quote":"demonstrating that sentiment information can be a stronger predictor for Bitcoin trading compared to the actual price"}]},"datasets":{"status":"available","items":[{"name":"FI-2010","provider":null,"kind":"order-book","access":"public","period":null,"universe":"5 NASDAQ stocks over 10 consecutive days","quote":"... contains 4 million time series data for five stocks from Nasqad Nordic market in a time frame of 10 consecutive days.","known_id":"fi-2010"},{"name":"Bitcoin and Ethereum price data","provider":null,"kind":"crypto-onchain","access":"public","period":null,"universe":"Cryptocurrencies Bitcoin and Etherium","quote":"on ... the popular cryptocurrencies BitCoin and Etherium."},{"name":"Financial dataset with 28 instrument combinations","provider":null,"kind":"market-prices","access":"unknown","period":"2009 to mid‑2018","universe":"28 different instrument combinations with currencies such as Euro, Dollar, British pounds ","quote":"evaluated on ... a financial dataset that contains 28 different instrument combinations with currencies such as Euro, Dollar, British pounds and Canadian dollar among others. The dataset contains minute price candles starting from 2009 to mid-2018."}],"known":[{"id":"fi-2010","name":"FI-2010","provider":"Ntakaris et al.","kind":"order-book","access":"public","quote":"The FI-2010 dataset contains 4 million time series data for five stocks from Nasqad Nordic market in a time frame of 10 consecutive days.","mentions":5,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"Commission fee c is applied each step as ct = |at−at−1|c and is set slightly higher than actual to cover slippage.","quote":"... c is typically set to a value slightly higher than the actual commission paid to account for price slippage and possible risks.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Commission fee c is applied each step as ct = |at−at−1|c and is set slightly higher than actual to cover slippage.","card_quote":"... c is typically set to a value slightly higher than the actual commission paid to account for price slippage and possible risks.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"PPO with the proposed price‑trailing method improves PnL from 23.5% ± 2.0% to 28.6% ± 2.4% and Sharpe ratio from 3.59 ± 0.37 to 4.20 ± 0.43.","kind":"performance","quote":"PnL 23.5% ± 2.0% → 28.6% ± 2.4% ... Sharpe ratio 3.59 ± 0.37 → 4.20 ± 0.43"},{"finding":"Adaptive normalization (RDAIN) outperforms static and other adaptive methods on FI‑2010 in terms of F1‑score and Cohen’s κ.","kind":"performance","quote":"it is evident that the proposed method outperforms all of the compared normalization methods, including an adaptive method (DAIN) lacking the gating mechanism"},{"finding":"Combining price with sentiment yields higher returns (10.55 ± 1.16) and Sharpe (156.68 ± 5.38) than price only (9.68 ± 4.93, 149.08 ± 5.37).","kind":"performance","quote":"Price only 9.68 ± 4.93 149.08 ± 5.37 ... Price + Sentiment 10.55 ± 1.16 156.68 ± 5.38"}],"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":1,"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":"2026-11-14T18:24:21Z"},"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/"}