"METIS" is a novel and powerful framework which supports to easily implement a decision support system for a target domain, a target purpose, and a target application using large-scale and heterogeneous data. METIS is short for ML-based Decision Support Information System. Based on the next-generation machine learning, it provides selected information that users really need (i.e., supports users’ decisions) by incorporating a variety of heterogeneous data into a unified modeling framework.

Our decision support system has four important and differentiated features compared to existing systems and generic technologies.

It supports easy and effective modeling on large-scale heterogeneous data based on the integrated modeling framework. It flexibly constructs models suitable for target domains, target applications, target services, and target data and learns them efficiently.

It manages dynamic data and models by using incremental learning. In other words, it efficiently reflects the data accumulated over time in the model at the previous time-stamp.

It preserves the privacy of user data by using federated model learning. It trains global models and improves their performances by considering a lot of user data without accessing users’ local data.

It provides good scalability and efficiency by fully utilizing limited resources. In terms of model learning, it efficiently processes large-scale data that conventionally can not be handled in a local device, where computation and memory resources are limited.

• Professor Hwanjo Yu (hwanjoyu@postech.ac.kr)

• Ph.D Student Junsu Cho (junsu7463@postech.ac.kr)

The code is licensed under the MIT License