Professionals knee-deep in drug discovery and development usually have a wealth of data at their fingertips. The question of how to make the most effective and efficient use of the available data is another matter entirely. Outsourcing-Pharma recently connected with Ajay Khanna, CEO and founder of Tellius, to discuss how advanced analytical tools like artificial intelligence (AI) can be put to work, to help make the best use possible of data. OSP: Could you please share the'elevator presentation' description of Tellius? AK: Tellius is an AI-powered analytics and decision intelligence platform that enables anyone, regardless of analytical skills, to quickly ask and answer'what', 'why', and'how'-type questions of their granular enterprise data in order to make better, faster decisions.

The worlds of AI and BI occupy distinct places in the analytics continuum, which is most often understood with concepts like descriptive analytics, predictive analytics, and prescriptive analytics. Users can leverage descriptive analytics and BI tools to explore what happened in the past, while predictive analytics makes use of ML models trained on real-world data to generate an educated guess about what will happen next. However, the lines separating these two camps are getting more blurry by the month. For years, Gartner has talked about how BI tool vendors are adding more ML and AI capabilities to their wares. In its latest Magic Quadrant for Analytics and BI Platforms, the firm talked about how the next generation of "augmented analytic" products will bring ML and AI to bear on things like data prep, query generation, and insight generation.

Tools such as Tellius, DataRobot, Dataiku and more help users to move faster through the machine learning workflow. AutoML automates aspects of ML such as feature transformation, model selection, explainability and management. After selecting the feature to predict (price), a histogram will be created along with a recommended model type and evaluation. As we are selecting a variable with a high number of discrete values, the recommended model types are regression. With AutoML, the emphasis is on moving quickly and ease-of-use.