Natural language based financial forecasting: a survey
Artificial Intelligence ReviewPublished 27 October 2017Open access
Frank Xing, Erik Cambria, Roy E. Welsch
Citations397
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This review article clarifies the scope of NLFF research by ordering and structuring techniques and applications from related work, and aims to increase the understanding of progress and hotspots in NLFF, and bring about discussions across many different disciplines.
Abstract
Natural language processing (NLP), or the pragmatic research perspective of computational linguistics, has become increasingly powerful due to data availability and various techniques developed in the past decade. This increasing capability makes it possible to capture sentiments more accurately and semantics in a more nuanced way. Naturally, many applications are starting to seek improvements by adopting cutting-edge NLP techniques. Financial forecasting is no exception. As a result, articles that leverage NLP techniques to predict financial markets are fast accumulating, gradually establishing the research field of natural language based financial forecasting (NLFF), or from the application perspective, stock market prediction. This review article clarifies the scope of NLFF research by ordering and structuring techniques and applications from related work. The survey also aims to increase the understanding of progress and hotspots in NLFF, and bring about discussions across many different disciplines.
Keywords
Computer ScienceDecision Sciences
The Journal of FinanceEfficient Capital Markets: A Review of Theory and Empirical Work
13,299 Citations1970Eugene F. Fama
Language<b>WordNet: An electronic lexical database</b> . Ed. by Christiane Fellbaum. Cambridge, MA: MIT Press, 1998. Pp. xxii, 423.
11,687 Citations2000Adam Kilgarriff
The lexical database: nouns in WordNet, George A. Miller modifiers in WordNet, Katherine J. Miller a semantic network of English verbs, and applications of WordNet: building semantic concordances are presented.
Mining and summarizing customer reviews
7,714 Citations2004Minqing Hu, Bing Liu
This research aims to mine and to summarize all the customer reviews of a product, and proposes several novel techniques to perform these tasks.
Communications of the ACMProbabilistic topic models
5,549 Citations2012David M. Blei
Surveying a suite of algorithms that offer a solution to managing large document archives suggests they are well-suited to handle large amounts of data.
International Journal of ForecastingAnother look at measures of forecast accuracy
5,343 Citations2006Rob J. Hyndman, Anne B. Koehler
Journal of Computational ScienceTwitter mood predicts the stock market
4,995 Citations2011Johan Bollen, Huina Mao +1 more
This work investigates whether measurements of collective mood states derived from large-scale Twitter feeds are correlated to the value of the Dow Jones Industrial Average (DJIA) over time and indicates that the accuracy of DJIA predictions can be significantly improved by the inclusion of specific public mood dimensions but not others.
NeurocomputingTime series forecasting using a hybrid ARIMA and neural network model
4,350 Citations2003G.Peter Zhang
Experimental results with real data sets indicate that the combined model can be an effective way to improve forecasting accuracy achieved by either of the models used separately.
IEEE Transactions on Information TheoryThree models for the description of language
2,749 Citations1956Noam Chomsky
It is found that no finite-state Markov process that produces symbols with transition from state to state can serve as an English grammar and the particular subclass of such processes that produce n -order statistical approximations to English do not come closer to matching the output of an English grammar.
SentiWordNet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining.
2,652 Citations2010Stefano Baccianella, Andrea Esuli +1 more
This work discusses SENTIWORDNET 3.0, a lexical resource explicitly devised for supporting sentiment classification and opinion mining applications, and reports on the improvements concerning aspect (b) that it embodies with respect to version 1.0.
The Journal of FinanceIs All That Talk Just Noise? The Information Content of Internet Stock Message Boards
2,400 Citations2004Werner Antweiler, Murray Z. Frank
Economic RecordPredicting the Present with Google Trends
2,304 Citations2012Hyunyoung Choi, Hal R. Varian
The Journal of FinanceMore Than Words: Quantifying Language to Measure Firms' Fundamentals
2,245 Citations2008Paul C. Tetlock, Maytal Saar‐Tsechansky +1 more
Journal of Accounting ResearchTextual Analysis in Accounting and Finance: A Survey
2,203 Citations2016Tim Loughran, Bill McDonald
BT Technology JournalConceptNet — A Practical Commonsense Reasoning Tool-Kit
1,560 Citations2004H Liu, Pankaj Kumar Singh
Communications of the ACMTechniques and applications for sentiment analysis
1,494 Citations2013Ronen Feldman
The main applications and challenges of one of the hottest research areas in computer science are revealed.
Information FusionA review of affective computing: From unimodal analysis to multimodal fusion
1,469 Citations2017Soujanya Poria, Erik Cambria +2 more
This first of its kind, comprehensive literature review of the diverse field of affective computing focuses mainly on the use of audio, visual and text information for multimodal affect analysis, and outlines existing methods for fusing information from different modalities.
Management ScienceYahoo! for Amazon: Sentiment Extraction from Small Talk on the Web
1,442 Citations2007Sanjiv Ranjan Das, Mike Y. Chen
A methodology for extracting small investor sentiment from stock message boards is developed, which comprises different classifier algorithms coupled together by a voting scheme.
The Journal of FinanceEconomic Links and Predictable Returns
1,375 Citations2008Lauren Cohen, Andrea Frazzini
Open information extraction from the web
1,323 Citations2007Michele Banko, Michael Cafarella +3 more
Journal of Empirical FinanceInvestor sentiment and the near-term stock market
1,305 Citations2003Gregory W. Brown, Michael T. Cliff
Journal of Personality AssessmentA Shortened Version of the Profile of Mood States
1,229 Citations1983Saya Shacham
The feasibility of using a shorter version of the Profile of Mood States is examined, indicating the suitability of the short version for estimating the original mood scale scores in this population of cancer patients.
IEEE Intelligent SystemsAffective Computing and Sentiment Analysis
1,179 Citations2016Erik Cambria
The emerging fields of affective computing and sentiment analysis, which leverage human-computer interaction, information retrieval, and multimodal signal processing for distilling people's sentiments from the ever-growing amount of online social data.
The Journal of FinanceThe Causal Impact of Media in Financial Markets
1,133 Citations2011Joseph Engelberg, Christopher A. Parsons
IEEE Computational Intelligence MagazineJumping NLP Curves: A Review of Natural Language Processing Research [Review Article]
1,022 Citations2014Erik Cambria, Bebo White
This survey article reinterprets the evolution of NLP research as the intersection of three overlapping curves-namely Syntactics, Semantics, and Pragmatics Curves which will eventually lead NLPResearch to evolve into natural language understanding.
Lecture notes in computer scienceMultiword Expressions: A Pain in the Neck for NLP
1,014 Citations2002Ivan A. Sag, Timothy Baldwin +3 more
The various kinds of multiword expressions should be analyzed in distinct ways, including listing "words with spaces", hierarchically organized lexicons, restricted combinatoric rules, lexical selection, "idiomatic constructions" and simple statistical affinity.
Journal of Business CommunicationAre Investors Influenced By How Earnings Press Releases Are Written?
868 Citations2008Elaine Henry
Knowledge-Based SystemsAspect extraction for opinion mining with a deep convolutional neural network
852 Citations2016Soujanya Poria, Erik Cambria +1 more
This paper used a 7-layer deep convolutional neural network to tag each word in opinionated sentences as either aspect or non-aspect word, and developed a set of linguistic patterns for the same purpose and combined them with the neural network.
Predicting the semantic orientation of adjectives
819 Citations1997Vasileios Hatzivassiloglou, Kathleen McKeown
ACM Transactions on Information SystemsTextual analysis of stock market prediction using breaking financial news
770 Citations2009Robert P. Schumaker, Hsinchun Chen
This research examines a predictive machine learning approach for financial news articles analysis using several different textual representations: bag of words, noun phrases, and named entities and found that a Proper Noun scheme performs better than the de facto standard of Bag of Words in all three metrics.
Journal of Economic Dynamics and ControlTime series properties of an artificial stock market
742 Citations1999Blake LeBaron, W. Brian Arthur +1 more
IEEE Intelligent SystemsDeep Learning-Based Document Modeling for Personality Detection from Text
665 Citations2017Navonil Majumder, Soujanya Poria +2 more
Expert Systems with ApplicationsSentiment analysis on social media for stock movement prediction
616 Citations2015Thien Hai Nguyen, Kiyoaki Shirai +1 more
This paper shows an evaluation of the effectiveness of the sentiment analysis in the stock prediction task via a large scale experiment and a novel method for predicting stock price movement using the sentiment from social media.
Expert Systems with ApplicationsText mining for market prediction: A systematic review
591 Citations2014Arman Khadjeh Nassirtoussi, Saeed Aghabozorgi +2 more
A comparative analysis of the systems based on market prediction based on online-text-mining expands onto the theoretical and technical foundations behind each and should help the research community to structure this emerging field and identify the exact aspects which require further research and are of special significance.
Convolutional MKL Based Multimodal Emotion Recognition and Sentiment Analysis
587 Citations2016Soujanya Poria, Iti Chaturvedi +2 more
A novel method to extract features from visual and textual modalities using deep convolutional neural networks and significantly outperform the state of the art of multimodal emotion recognition and sentiment analysis on different datasets is presented.
Expert Systems with ApplicationsComputational Intelligence and Financial Markets: A Survey and Future Directions
579 Citations2016Rodolfo C. Cavalcante, Rodrigo C. Brasileiro +3 more
International Conference on Artificial IntelligenceDeep learning for event-driven stock prediction
557 Citations2015Xiao Ding, Yue Zhang +2 more
This work proposes a deep learning method for event-driven stock market prediction that can achieve nearly 6% improvements on S&P 500 index prediction and individual stock prediction, respectively, compared to state-of-the-art baseline methods.
Handbook of computational economicsChapter 23 Heterogeneous Agent Models in Economics and Finance
525 Citations2006Cars Hommes
Expert Systems with ApplicationsA Bayesian regularized artificial neural network for stock market forecasting
507 Citations2013Jonathan L. Ticknor
The results indicate that the proposed Bayesian regularized artificial neural network performs as well as the more advanced models without the need for preprocessing of data, seasonality testing, or cycle analysis.
Knowledge-Based SystemsNews impact on stock price return via sentiment analysis
486 Citations2014Xiaodong Li, Haoran Xie +3 more
Results show that at individual stock, sector and index levels, the models with sentiment analysis outperform the bag-of-words model in both validation set and independent testing set, and the models which use sentiment polarity cannot provide useful predictions.
The Journal of FinanceThe Weekend Effect: Trading Patterns of Individual and Institutional Investors
486 Citations1990Josef Lakonishok, Edwin D. Maberly
OpinionFinder
471 Citations2005Theresa Wilson, Paul Hoffmann +7 more
OpinionFinder is a system that performs subjectivity analysis, automatically identifying when opinions, sentiments, speculations, and other private states are present in text.
SciencePrediction and explanation in social systems
438 Citations2017Jake M. Hofman, Amit Sharma +1 more
It is argued that the increasingly computational nature of social science is beginning to reverse this traditional bias against prediction; however, it has also highlighted three important issues that require resolution, which will lead to better, more replicable, and more useful social science.
IEEE Intelligent SystemsSentiment Analysis Is a Big Suitcase
417 Citations2017Erik Cambria, Soujanya Poria +2 more
The authors argue that there are (at least) 15 NLP problems that need to be solved to achieve human-like performance in sentiment analysis, and address the composite nature of the problem via a three-layer structure inspired by the “jumping NLP curves” paradigm.
Expert Systems with ApplicationsThe impact of microblogging data for stock market prediction: Using Twitter to predict returns, volatility, trading volume and survey sentiment indices
369 Citations2016Nuno Oliveira, Paulo Cortez +1 more
Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora
359 Citations2016William L. Hamilton, Kevin B. Clark +2 more
The approach achieves state-of-the-art performance on inducing sentiment lexicons from domain-specific corpora and that the purely corpus-based approach outperforms methods that rely on hand-curated resources (e.g., WordNet).
Decision Support SystemsAutomated news reading: Stock price prediction based on financial news using context-capturing features
343 Citations2013Michael Hagenau, Michael Liebmann +1 more
It is shown that a robust feature selection allows lifting classification accuracies significantly above previous approaches when combined with complex feature types and reduces the problem of over-fitting when applying a machine learning approach.
Applied Soft ComputingArtificial neural networks in business: Two decades of research
339 Citations2015Michal Tkáč, Robert Verner
A literature review considering articles on artificial neural networks in business published in last two decades revealed that most of the research has aimed at financial distress and bankruptcy problems, stock price forecasting, and decision support, with special attention to classification tasks.
Decision Support SystemsEvaluating sentiment in financial news articles
311 Citations2012Robert P. Schumaker, Yulei Zhang +2 more
Investigation of the Arizona Financial Text system, a financial news article prediction system, and a sentiment analysis tool found that subjective news articles were easier to predict in price direction and using a simple trading engine, subjective articles garnered a 3.30% return.
Lecture notes in computer scienceThe Hourglass of Emotions
302 Citations2012Erik Cambria, Andrew Livingstone +1 more
A novel biologically-inspired and psychologically-motivated emotion categorisation model that represents affective states both through labels and through four independent but concomitant affective dimensions, which can potentially describe the full range of emotional experiences that are rooted in any of us.
Correlating financial time series with micro-blogging activity
276 Citations2012Eduardo Ruiz, Vagelis Hristidis +3 more
The problem of correlating micro-blogging activity with stock-market events, defined as changes in the price and traded volume of stocks, is studied and it is shown that even relatively small correlations between price and micro- bloggers features can be exploited to drive a stock trading strategy that outperforms other baseline strategies.
Knowledge-Based SystemsA survey of the applications of text mining in financial domain
261 Citations2016B. Shravan Kumar, Vadlamani Ravi
A state-of-the-art survey of various applications of Text mining to finance, categorized broadly into FOREX rate prediction, stock market prediction, customer relationship management (CRM) and cyber security.
OPUS (Augsburg University)SenticNet 4: A Semantic Resource for Sentiment Analysis Based on Conceptual Primitives
261 Citations2016Erik Cambria, Soujanya Poria +2 more
SenticNet 4 overcomes limitations by leveraging on conceptual primitives automatically generated by means of hierarchical clustering and dimensionality reduction.
Information SciencesThe effect of news and public mood on stock movements
257 Citations2014Qing Li, Tiejun Wang +4 more
A quantitative media-aware trading strategy is proposed to investigate the media impact on stock markets and finds that fundamental information of firm-specific news articles can enrich the knowledge of investors and affect their trading activities.
Topic Modeling based Sentiment Analysis on Social Media for Stock Market Prediction
250 Citations2015Thien Hai Nguyen, Kiyoaki Shirai
The results show that incorporation of the sentiment information from social media can help to improve the stock prediction.
ACM Transactions on Information SystemsSound and complete relevance assessment for XML retrieval
241 Citations2008Benjamin Piwowarski, Andrew Trotman +1 more
Investigations into the creation of sound and complete relevance assessments for the evaluation of content-oriented XML retrieval as carried out at INEX, the evaluation campaign for XML retrieval are described.
Communications of the ACMMining business databases
235 Citations1996Ronald J. Brachman, Tom Khabaza +3 more
The goal here is to provide a brief overview of the key issues in knowledge discovery in an industrial context and outline representative applications.
Artificial Intelligence ReviewFinancial credit risk assessment: a recent review
213 Citations2015Ning Chen, Bernardete Ribeiro +1 more
Statistical ScienceParrondo's paradox
210 Citations1999Derek Abbott, Gregory P. Harmer
Parrondo’s paradox is introduced and a heuristic explanation of the phenomenon in terms of a Brownian ratchet model is developed, having possible applications in electronic signal processing and its impact on stock market models is also an interesting open question.
Proceedings of the AAAI Conference on Artificial IntelligenceOnline ARIMA Algorithms for Time Series Prediction
191 Citations2016Chenghao Liu, Steven C. H. Hoi +2 more
This paper proposes online learning algorithms for estimating ARIMA models under relaxed assumptions on the noise terms, which is suitable to a wider range of applications and enjoys high computational efficiency.
Decision Support SystemsStock market sentiment lexicon acquisition using microblogging data and statistical measures
184 Citations2016Nuno Oliveira, Paulo Cortez +1 more
It is shown that the new lexicons are competitive for measuring investor sentiment when compared with six popular lexicons, and can be used alternatively to traditional survey indicators with advantages (e.g., cheaper creation, higher frequencies).
Annual Review of Financial EconomicsBayesian Portfolio Analysis
183 Citations2010Doron Avramov, Guofu Zhou
Decision Support SystemsAn intraday market risk management approach based on textual analysis
168 Citations2010Sven S. Groth, Jan Muntermann
Evaluation results provide strong evidence that unstructured (textual) data represents a valuable source of information also for financial risk management - a domain in which, in the past, little attention has been paid to unstructuring data.
Journal of Conflict ResolutionPredicting Conflict in Space and Time
165 Citations2010Nils B. Weidmann, Michael D. Ward
Daily stock market forecast from textual web data
164 Citations2002Beat Wüthrich, Vincent Cho +4 more
The aim is to predict stock markets using information contained in articles published on the Web, mostly textual articles appearing in the leading and influential financial newspapers, to produce periodically forecasts in stock markets.
International Conference on Computational LinguisticsA Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks
162 Citations2016Soujanya Poria, Erik Cambria +2 more
This work develops models based on a pre-trained convolutional neural network for extracting sentiment, emotion and personality features for sarcasm detection and addresses the often ignored generalizability issue of classifying data that have not been seen by the models at learning phase.
Journal of the Franklin InstituteBayesian network based extreme learning machine for subjectivity detection
159 Citations2017Iti Chaturvedi, Edoardo Ragusa +3 more
This paper extends the extreme learning machine (ELM) paradigm to a novel framework that exploits the features of both Bayesian networks and fuzzy recurrent neural networks to perform subjectivity detection and proves its capacity to address portability across languages in translation tasks.
Artificial IntelligenceMoving average reversion strategy for on-line portfolio selection
149 Citations2015Bin Li, Steven C. H. Hoi +2 more
This article proposes a multiple-period mean reversion, or so-called "Moving Average Reversion" (MAR), and a new on-line portfolio selection strategy named "On-Line Moving Average Reverting" (OLMAR), which exploits MAR via efficient and scalable online machine learning techniques.
Language models for financial news recommendation
142 Citations2000Victor Lavrenko, Matt Schmill +4 more
It is demonstrated that stories re ommended by nalyst ould be used to pro tably predi t forth oming trends in sto k pri es.
Business & Information Systems EngineeringUsing Twitter to Predict the Stock Market
136 Citations2015Michael Nofer, Oliver Hinz
A significant relationship between aggregate Twitter mood states and the stock market is not found and a trading strategy for the German stock market is created, which increases by up to 36 % within a six-month period after the consideration of transaction costs.
Decision Support SystemsSentiment analysis in financial texts
136 Citations2016Samuel W. K. Chan, Mickey W. C. Chong
This study addresses key questions related to the explosion of interest in how to extract insight from unstructured data and how to determine if such insight provides any hints concerning the trends of financial markets and proposes a sentiment analysis engine (SAE) which takes advantage of linguistic analyses based on grammars.
Decision Support SystemsFinancial fraud detection using vocal, linguistic and financial cues
126 Citations2015Kenneth D. Morton, William J. Mayew +2 more
Optimization results reveal that only a subset of the complete set of numeric, linguistic and vocalic predictors enhance overall predictive accuracy, which should assist investors, financial analysts and regulators in identifying the most effective markers of corporate fraud.
Knowledge-Based SystemsGuest Editorial: Big Social Data Analysis
122 Citations2014Erik Cambria, Haixun Wang +1 more
The contained articles in this issue cover variegated topics including stock market prediction, political forecasting, time-evolving opinion mining, social network analysis, and human–robot interaction.
International Conference on Computational LinguisticsLabel Embedding for Zero-shot Fine-grained Named Entity Typing.
118 Citations2016Yukun Ma, Erik Cambria +1 more
A label embedding method that incorporates prototypical and hierarchical information to learn pre-trained label embeddings and a zero-shot learning framework that can predict both seen and previously unseen entity types are presented.
Online discovery and maintenance of time series motifs
117 Citations2010Abdullah Mueen, Eamonn Keogh
This paper develops the first online motif discovery algorithm which monitors and maintains motifs exactly in real time over the most recent history of a stream and allows useful extensions of the algorithm to deal with arbitrary data rates and discovering multidimensional motifs.
Knowledge-Based SystemsLearning word dependencies in text by means of a deep recurrent belief network
117 Citations2016Iti Chaturvedi, Yew-Soon Ong +3 more
Exploiting Social Relations and Sentiment for Stock Prediction
113 Citations2014Jianfeng Si, Arjun Mukherjee +4 more
Results demonstrate that topic senti- ments from close neighbors are able to help prove the prediction of a stock markedly and show that social sentiment about stock topics and stock relationship topics are predictive of each stock's market.
Stock prediction: Integrating text mining approach using real-time news
111 Citations2003Gabriel Pui Cheong Fung, Jeffrey Xu Yu +1 more
This paper proposes a systematic framework for mining multiple time series based on Efficient Market Hypothesis and explores the opportunity for mining textual documents and time series concurrently to predict stock prices based on news articles.
A review of stock market prediction with Artificial neural network (ANN)
107 Citations2013Chang Sim Vui, Gan Kim Soon +3 more
The aim of this paper is to provide a review of the applications of ANN in stock market prediction in order to determine what can be done in the future.
Lecture notes in computer scienceAn Introduction to Concept-Level Sentiment Analysis
97 Citations2013Erik Cambria
Journal of Behavioral FinanceReuters Sentiment and Stock Returns
93 Citations2014Matthias Uhl
It is shown that Reuters sentiment can explain and predict changes in stock returns better than macroeconomic factors and negative Reuters sentiment has more predictive power than positive Reuters sentiment.
Communications of the ACMComputationally modeling human emotion
93 Citations2014Stacy Marsella, Jonathan Gratch
This paper presents computer models of emotion, which inform theories of human intelligence and advance human-centric applications, and their applications in medicine and science.
Decision Support SystemsA text-based decision support system for financial sequence prediction
86 Citations2011Samuel W. K. Chan, James Franklin
A novel text-based decision support system (DSS) that extracts event sequences from shallow text patterns, and predicts the likelihood of the occurrence of events using a classifier-based inference engine, while preserving robustness and without indulging in formalism is proposed.
Journal of Economics and International FinanceApplication of data mining techniques in stock markets: A survey
71 Citations2010Ehsan Hajizadeh, Hamed Davari Ardakani +1 more
An overview of application of data mining techniques such as decision tree, neural network, association rules, factor analysis and etc in stock markets and progressive applications in addition to existing gap and less considered area are revealed.
Decision Support SystemsMedia-aware quantitative trading based on public Web information
70 Citations2014Qing Li, Tiejun Wang +4 more
A media-aware quantitative trading strategy utilizing sentiment information of Web media is proposed, achieved by capturing public mood from interactive behaviors of investors in social media and studying the impact of firm-specific news sentiment on stocks along with such public mood.
Journal of Statistical Planning and InferenceCopula-based regression models: A survey
69 Citations2009Nikolai Kolev, Delhi Paiva
Automatic Domain-Specific Sentiment Lexicon Generation with Label Propagation
63 Citations2013Yen-Jen Tai, Hung‐Yu Kao
This work proposes a framework to automatically generate sentiment lexicon by determining the semantic similarity between two words in the entire unlabeled corpus and treating the words as nodes and similarities as weighted edges to construct word graphs.
Time-Annotated Sequences for Medical Data Mining
61 Citations2007Michele Berlingerio, Francesco Bonchi +2 more
IEEE Computational Intelligence MagazineAn Introduction to Evolutionary Computation in Finance
59 Citations2008Anthony Brabazon, Michael O’Neill +1 more
This article provides an overview of some of these applications concentrating on those employing an evolutionary computation approach in finance.
IEEE Intelligent SystemsDynamic Business Network Analysis for Correlated Stock Price Movement Prediction
54 Citations2015Wenping Zhang, Chunping Li +3 more
The design of a novel business network-based model called the energy cascading model (ECM) for predicting directional stock price movements of related firms, which considers both influential business relationships and Twitter sentiments to infer a firm's middle to long-term directional stock prices.
Finance and Economics Discussion SeriesNews versus Sentiment: Predicting Stock Returns from News Stories
52 Citations2016Steven L. Heston, Nitish Ranjan Sinha
This paper uses a dataset of more than 900,000 news stories to test whether news can predict stock returns, and measures sentiment with a proprietary Thomson-Reuters neural network.
Proceedings of the AAAI Conference on Artificial IntelligenceTensor-Based Learning for Predicting Stock Movements
51 Citations2015Qing Li, Li-ling Jiang +2 more
This article proposes a supervised tensor regression learning approach to investigate the joint impact of different information sources on stock markets and shows that this approach outperforms the state-of-the-art trading strategies.
Proceedings of the AAAI Conference on Artificial IntelligenceDoubly Regularized Portfolio with Risk Minimization
50 Citations2014Weiwei Shen, Jun Wang +1 more
This paper proposes a doubly regularized portfolio that provides a modest but effective solution to the above difficulty and demonstrates a superior performance of having both higher risk-adjusted returns and dramatically decreased transaction volumes.
SOPS: Stock Prediction Using Web Sentiment
50 Citations2007Vivek Kumar Sehgal, Charles Song
A novel way to do stock market prediction based on sentiments of web users is introduced, which is able to predict the sentiment with high precision and shows that the stock performance and its recent web sentiments are also closely correlated.
ComplexityFiniteness of variance is irrelevant in the practice of quantitative finance
44 Citations2008Nassim Nicholas Taleb
ADMIRAL: A Data Mining Based Financial Trading System
44 Citations2007Gil Rachlin, Mark Last +2 more
The ADMIRAL system is simulated and evaluated on real-world series of news stories and stocks data using the C4.5 decision tree induction algorithm for predictive accuracy and profitability of each trading strategy using these predictions.
…