We previously described how Spartan Capital Intelligence (SCI) uses machine learning/artificial intelligence (ML/AI) to forecast stock prices and provide timely financial advice. For machine learning and forecasting to work, large amounts of high-quality data need to be gathered. The forecasts developed by machine learning depends on the quantity and quality of data that is fed into the analysis in a timely manner. You may ask, what technology does SCI leverage on to enhance the accuracy, completeness and timeliness of the financial data gathered and used for forecasting?
SCI utilizes tools that can capture thousands of financial data points in seconds. And this is made possible by eXtensible Business Reporting Language (XBRL) – an open source, xml-based format by which US publicly listed companies are required to use in financial reporting. At its core, XBRL calls for the development of standardized digital tags (XBRL Taxonomy) in order to label, classify and give relevant meaning to each piece of data with reference to a financial reporting standard/s. Think of the it as a dictionary, it does not only give the definition, but it also provides information on the key characteristics, and in some cases, even the translation to other languages, of a financial or non-financial data.
The XBRL technology was designed to enhance the transparency, accuracy and completeness of financial reporting and improve the efficiency of data capture and distribution. This technology is becoming increasingly more relevant in terms of transparency that even the US government publishes and distributes its spending data in XBRL format. In terms of data accuracy, it incorporates validation rules that minimize errors in financial values. Data completeness is mainly improved by the taxonomy, itself, through digital links (linkbases) that connects one data to another. Because of this, XBRL plays a significant role in enhancing the reliability of the data that we use in creating our machine learning models.
US publicly listed companies periodically submit their financial reports in XBRL format, as mandated by the U.S. SEC. These XBRL files are captured by our XBRL-enabled tools and are fed to our machine learning models in a matter of minutes upon submission. This enables SCI to run its ML/AI models using more accurate, complete and timely financial data that ultimately results in robust financial advice that you can access through our user-friendly AI platform or receive via your mobile devices through our notifications and alerts that you can configure based on the companies that you want to track.
To celebrate our upcoming launch we are running a contest (until Feb 7th), giving 100 free annual subscriptions to access our advisory platform.