A social media analytics application to measure twitter metrics of audience demographics, volume, engagement and interactions to capture market sentiment for the finance industry
Using qualitative and quantitative methods, Social Market Analytics (SMA) filters and analyzes Twitter accounts and individual tweets related to financial securities to provide clean, actionable data on market sentiment to investor clients. This data helps SMA’s clientele reduce risks, increase returns and generate new trade ideas.
SSI’s team of architects and developers helped SMA realized its vision through a web- based application. SSI defined the technology roadmap, did the complete front-end development, and built reliable application programming interfaces that transmit financial data to clients in easily accessible charting formats. The solution was based on transforming tremendous amount of social media data into S-Factor values.
The Extractor accesses data captured, containing commentary on the members of the client's stock universe, from social media sources through the API web services of Twitter and GNIP. The Extractor takes polls of Twitter every minute. This acquisition process continuously cycles through the universe list, adaptively polling for securities with current content in the message stream.
The Evaluator removes spam and duplicates and analyzes each tweet for financial market relevance to the entities in the client's stock universe. These are called “indicative” tweets, as these indicate expressions of market trading sentiment for stocks. The Evaluator uses proprietary natural language processing algorithms to asses each message. In short, the Evaluator utilizes tweet content and characteristics of the individuals tweeting to refine the intentions of professional investors.
The Calculator calculates the sentiment signatures for each member of the client's stock universe. A bucketing and weighting process operates on an entity’s indicative tweets and then groups these into time period buckets based on the arrival time of each tweet in the Calculator. A Normalization and Scoring process calculates the S-Score™ and other S-Factors™ for each entity with active content at the time of the estimate.
By helping SMA keep clients alerted to investor sentiment in real time, SSI has also helpedSMA grow from a startup to a highly profitable company. Trading companies like StockTwits have joined hands with the client to produce similar S-Factors™ based on StockTwits social data. SMA now has a range of business partners such as Markit, the New York Stock Exchange, Deltix, OneMarketData and EOTPRO Developments.