AuDaS: Automated Data Scientist
AuDaS is a Machine Learning platform that allows anyone with or without a background in Data Science to automatically:
• Load and prepare data
• Build and operationalize business decisioning solutions
• Build and operationalize Time Series applications
AuDaS provides an extremely user-friendly, clutter free interface that guides you through the solution building process:
1. Uploading the data
2. Applying relevant data-preprocessing steps suggested by the Adviser
3. Selecting the “type” of solution you wish AuDaS to build
AuDaS will then automatically assemble the optimal Data Science pipeline for your task which you can then run on new data-sets or integrate in your existing processes and applications through the RESTful API.
Request an AuDaS Trial
Building profitable Machine Learning applications is challenging and very few models ever make it to production. The main reasons are:
• Data is rarely clean or in the right format
• Machine Learning models risk overfitting which would lead to results that don’t generalize
• The computation is intractable
• There is a global shortage of Data Scientists
AuDaS implements and validates Machine Learning solutions in a framework that guarantees the generalisability on new data sets. Moreover, AuDaS reasons in a principled framework which provides:
• Confidence bounds for its predictions
• Transparency and interpretability of the results
• Actionable insights, forecasts and predictions
• The ability to integrate domain expertise
AuDaS allows you to easily build Classification, Regression, Clustering pipelines for all types of data including Time Series and which are optimally chosen and tuned for your problem.
Most business decisioning problems involve predicting the category of a new observation. For example, is this transaction fraudulent or not, will this project fail or not?
Regression is for predicting a continuous output such as what is the likely total cost for an insurance claim?
Clustering helps identify groups of points in your data sets which share similar properties. This can help detect categories you weren’t aware of.
Time Series Analysis
Time Series classification involves making a decision on for example, “who is speaking in this audio clip?” or which trend is present.
Also referred to as windowed classification, it involves making decisions at a given point in time. For example, predicting whether an undesirable event in a mobile network is likely to occur in the next hour?
Similar to annotation, forecasting involves predicting the value of a variable at a given point in time, but in this case the variable is continuous, for example the price of a stock or the number of orders placed on my website.
AuDaS automatically handles all your model validation for you from the data preparation, to model training and optimisation which guarantees the generalisable predictive power of its solutions.
by Charles Brecque on 17/10/2018 at 14:11
Solving the Kaggle Telco Customer Churn challenge in minutes using AuDaSAuDaS is the automated Data Scientist developed by Mind Foundry which aims to allow anyone, with or without a background in Data Science to easily build and deploy quality controlled Machine Learning pipelines. AuDaS empowers Business Analysts and Data Scientists by allowing them to easily insert their domain expertise in the model building process and extract actionable insights.In this tutorial we are going to see […]
Team and Resources
Mind Foundry is an Oxford University spin-out founded by Professors Stephen Roberts and Michael Osborne who have 35 person years in data analytics. The Mind Foundry team is composed of over 30 world class Machine Learning researchers and elite software engineers, many former post-docs from the University of Oxford. Moreover, Mind Foundry has a privileged access to over 30 Oxford University Machine Learning PhDs through its spin-out status. Mind Foundry is a portfolio company of the University of Oxford and its investors include Oxford Sciences Innovation, the Oxford Technology and Innovations Fund, the University of Oxford Innovation Fund and Parkwalk Advisors.