Applications of Applications of news analytics in finance: news analytics in finance: a reviewa reviewGautam Mitra Co-author Leela MitraSummary and scopeSummary and scopeIn this talk we set out a structured (reading) guide to the published research outputs: Journal papers, white papers, case studies which are emerging in the domain of “news analytics” applied to finance.We aim to provide insight into the subtle interplay of information technology (including AI), the quantitative models and behavioural biases in the context of trading and investment decisions.Applications such as low frequency and high frequency trading are presented; some desirable/potential applications are discussed.OutlineOutlinelIntroductionlNews datalData sourceslPre analysis of datalDetermining sentiment scoreslGeneral overviewlDas and ChenlLolModels and applications in summary forml(abnormal ) ReturnslVolatility and risk controllDesirable industry applicationslSummary and discussionsNews.Market Environment.Sentiment.Investment Decisions.Risk Control.IntroductionIntroductionTraders High Frequency Fund Managers Low Frequency Desktop Market Data NewsWireData WareHouseDataMartIntroductionIntroductionR Information SystemsAI, in particular, Natural Language ProcessingFinancial Engineering/quantitative Modelling( including behavioural finance )IntroductionIntroductionIntroductionIntroductionData analysis Datamart quant modelsMainstream NewsPre-NewsWeb 2.0 Social MediaPre-AnalysisClassifiersSentiment Scores(Numeric) financial market dataAnalysisConsolidated DatamartUpdated beliefs, Ex-ante view of market environmentQuant Models1. Return Predictions 2. Fund Management / Trading Decisions 3. Volatility estimates and risk controlOutlineOutlinelIntroductionlNews datalData sourceslPre analysis of datalDetermining sentiment scoreslGeneral overviewlDas and ChenlLolModels and applications in summary forml(abnormal) ReturnslVolatility and risk controllDesirable industry applicationslSummary and discussionsNews data: Data sourcesNews data: Data sourcesSources of news/informational flows (Leinweber)News: Mainstream media, reputable sources. Newswires to traders desks.Newspapers, radio and TV.Pre-News: Source data SEC reports and filings. Government agency reports. Scheduled announcements, macro economic news, industry stats, company earnings reportsSocial media: Blogs, websites and message boardsQuality can vary significantlyBarriers to entry lowHuman behaviour and agendasNews data: Data sourcesNews data: Data sourcesWeb based newsIndividual investors pay more attention than institutional investors (Das and Rieger)“Collective Intelligence” large group of people (no ulterior motives) their collective opinion may be useful.SEC does monitor message boardsFar from perfect vetting of information.Financial news can be split betweenScheduled news (Synchronous)Unscheduled news (Asynchronous, event driven)News data: Data sourcesNews data: Data sourcesScheduled news (Synchronous)Arrives at pre scheduled timesMuch of pre news Structured formatOften basic numerical formatTypically macro economic announcements and earnings announcementsNews data: Data sourcesNews data: Data sourcesMacro economic announcements Widely used in automated tradingImpact large and most liquid markets (foreign exchange, Govt. debt, futures markets)Naturally affects trading strategies.Speed and accuracy are key. technology requirements substantialProviders in this spaceTrade the News, Need to Know News, Market News International, Thomson Reuters, Dow Jones, Bloomberg Earnings announcementsDirectly influences stock pricesWidely anticipated and used in trading strategiesNews data: Data sourcesNews data: Data sourcesUnscheduled news (Asynchronous, event driven) Arrives unexpectedly over timeMainstream news and social media Unstructured, qualitative, textual formNon-numeric Difficult to process quickly and quantitativelyMay contain information about effect and cause of an eventTo be applied in quant models needs to be converted to an input time seriesOutlineOutlinelIntroductionlNews datalData sourceslPre analysis of datalDetermining sentiment scoreslGeneral overviewlDas and ChenlLolModels and applications in summary forml(abnormal) ReturnslVolatility and risk controllDesirable industry applicationslSummary and discussionsNews data: Pre analysis of dataNews data: Pre analysis of dataCollecting, cleaning and analysing news data challengingMajor newswire providers collect news from a wide range of sources e.g. Factiva database from Dow Jones, news from 400 sourcesTagging Machine readable meta dataMajor newswire providers tag incoming news storiesReporters tag stories as they enter them to systemMachine learning techniques also used to identify relevant tags (RavenPack)Unstructured stories into basic machine readable formTags held in XML Reveals storys topic areas and other usef