The financial trading sector has witnessed a number of APIs appear on the trading scene over the past few years (e.g. TradeKing, Data Explorers, etc.). However, the data pulled from most of these financial APIs concentrates on the numbers (e.g. shares bought, shares sold, ROIC, debt metrics, etc.). Last week, "SNTMNT [launched] the first API worldwide that gives predictions based on Twitter sentiment about future stock price movement for all S&P 500 stocks." Although the data behind the number-centric APIs has sharpened trading tools and given traders valuable insight into financial data, the SNTMNT API offers the other side of the trading coin: traders' concerns and certainties. SNTMNT offers three APIs: Trading Indicator API, Financial Sentiment API, and Brand Sentiment API. The Trading Indicator API "gives hourly and/or daily buy & sell signals for all S&P 500 stocks based on online sentiment on Twitter." The Financial Sentiment API "is specifically trained to deal with unstructured context and financial jargon" and captures the overall market sentiment from the collected tweets. The Brand Sentiment API is "tailored to brands, products & company information." Depending on the API, SNTMNT boasts of accuracy rates from 60% - 80%. Driving the APIs is a "Machine learning algorithm that generates an indicator predicting share price movement." First, Tweets are gathered regarding specific stocks, key content is extracted from the tweets, and the content is filtered through the algorithm to generate the sentiment. SNTMNT blossomed out of Startup Weekend Amsterdam 2011. Since its birth, SNTMNT has received substantial press, and developed strategic anchor partnerships. Should the API continue a positive success rate in gauging market sentiment, the financial trading sector may have a new star on its hands.
Eric Carter, Contributing Writer, Dartsand