AI technologies such as machine learning have become an industry standard for supply chain forecasting and planning. However, the recent global pandemic, geopolitical situation and climate change caused unprecedented disruptions that challenge even the savviest supply chain leaders. Join Dr. Devavrat Shah, professor and a director of Statistics and Data Science Center at MIT and a CTO and co-founder of Ikigai Labs (ikigailabs.io), to learn how AI and data can help you reduce variability and optimize inventory levels. In this webinar, Devavrat will explain three innovative technologies and demonstrate their application to real-world supply chain problems, specifically: - How multivariate time series forecasting helps predict demand when large sets of historical data are not available - How to use reinforcement learning to optimize your supply chain operations for your desired business outcomes - What is DeepMatch and how it helps stitch together data from any sources

Welcome to Ikigai! This is a short onboarding tutorial to get you started in minutes. In this video, we will be creating a simple flow that selects a few columns and saves the output. Please start a free trial to follow along.

Introducing Ikigai, an end-to-end AI-powered data platform that enables business users to connect their data and leverage no-code AI/ML with just a few clicks to drive insights and actions through interactive dashboards without IT or data scientists. ​

In Episode 2 of Data, Operations, AI, and People [DOAP], Devavrat Shah, Ikigai Labs’ CTO and co-founder, chats with Munther Dahleh—the founding director of IDSS at MIT. Together, they discuss IDSS and the role of data, data in organizations, and the role of education in creating data-enabled decision-makers.

Gaining insights into your business should be easier. DOAP, brought to you by Ikigai Labs co-founders Vinayak Ramesh and Devavrat Shah, features discussions on perfecting the synergy between data, AI, and humans with special guests. Start transforming your business by tuning into these episodes now.

DeepCast capability only needs as little as three weeks' worth of data to develop dynamic insights and build complex forecasting models.