FICO Analytics Workbench
Predictive Modeling with Machine Learning and Explainable AI. FICO® Analytics Workbench™ is an integrated suite of state-of-the-art analytic authoring tools that empowers companies to improve business decisions across the customer lifecycle. With it, data scientists can build superior decisioning capabilities using a wide range of predictive data modeling tools and algorithms, including the latest machine learning (ML) and explainable artificial intelligence (xAI) approaches. We enhance the best of open source data science and machine learning with innovative intellectual property from FICO to deliver world-class analytic capabilities to discover, combine, and operationalize predictive signals in data. Analytics Workbench is built on the leading FICO® Platform to allow new predictive models and strategies to be deployed into production with ease.
Learn more
Arena Autonomy OS
Arena empowers businesses across industries to make high-frequency, critical path decisions fully autonomous. Autopilot for high-frequency business decisions. Similar to a physical robot, Autonomy OS is composed of three components, the sensor, the brain, and the arm. The sensor measures, the brain makes decisions, and the arm takes action. The whole system operates automatically and in real time. Autonomy OS ingests and encodes heterogeneous data with different latency profiles, from streaming real-time and structured time series, to unstructured data like images and text, into features that train machine learning models. Autonomy OS also augments data with contextual data from Arena’s Demand Graph, a daily updating index of factors that affect consumer demand and supply, from product prices and availability by location, to demand proxies from social media platforms. Customer preferences and behaviors change, supply routes are unexpectedly disrupted, and competitors alter strategy.
Learn more
Amazon SageMaker Feature Store
Amazon SageMaker Feature Store is a fully managed, purpose-built repository to store, share, and manage features for machine learning (ML) models. Features are inputs to ML models used during training and inference. For example, in an application that recommends a music playlist, features could include song ratings, listening duration, and listener demographics. Features are used repeatedly by multiple teams and feature quality is critical to ensure a highly accurate model. Also, when features used to train models offline in batch are made available for real-time inference, it’s hard to keep the two feature stores synchronized. SageMaker Feature Store provides a secured and unified store for feature use across the ML lifecycle. Store, share, and manage ML model features for training and inference to promote feature reuse across ML applications. Ingest features from any data source including streaming and batch such as application logs, service logs, clickstreams, sensors, etc.
Learn more