A Web-based system of interlocking tools for quantitative analysis.

TwoRavens is a platform for machine learning that allows a domain expert, in concert with our system, to complete a high quality, predictive and interpretable model without any statistical or machine learning expertise. To do so, the system facilitates intuitive machine learning and model interpretation, model discovery, and data exploration. As our intelligent back-end automatically seeks interesting relationships in the data and builds models to predict outcomes, researchers impart substantive knowledge about their data and own research questions to guide the automated generation of AI assistance for data analysis in an interactive paradigm we call human-guided machine learning.

Philosophy

In the very best research settings, where there are collaborations between domain experts and data scientists or statistical experts, exploration into the data is a joint venture where statisticians drive the computational machinery of analysis, but are directed to the interesting features by the knowledge of the domain expert. Our belief is that you can automate much of what the statistician brings, but the domain expert remains central to the task. Thus, our goal is to augment the domain expert, leading to the construction of high quality, impactful and interpretable models.

Applications

Machine Learning The goal of the machine learning application is to allow the domain expert, in concert with our system, to complete a high quality, predictive and interpretable model without a statistical expert or data scientists. To do so, the system facilitates intuitive machine learning and model interpretation, model discovery, and data exploration. As our intelligent back-end automatically seeks interesting relationships in the data and builds models to predict outcomes, researchers impart substantive knowledge about their data and own research questions to guide the automated generation of AI assistance for data analysis in an interactive paradigm we call human-guided machine learning.

Event Data The event data module is designed for researchers to easily structure raw event data into usable time series formats. Researchers can browse openly available event datasets, construct queries to select types of events and sets of actors, view and download resulting time-series data, and export data to our main system for AI assisted analysis.

Metadata The metadata service is our data profiler. It provides the bulk of the initial information used to visualize the front-end interfaces, including distributions, summaries, and data types.