Zachary Pardos, Professor

Closed (1) Supporting undergraduate decision making with big data and adaptive technologies

Applications for Spring 2019 are now closed for this project.

The AskOski project ( is a research and development effort lead by Professor Pardos to transfer the latest in big data and machine learning research to the domain of course guidance in higher ed. The project has two foci: (1) machine learning research applied to big data from education contexts and (2) the continued development and evaluation of a recommender system. The recommender system is live in-production at Berkeley and is planned for deployment at another UC and a community college by Fall '19.

There are two available roles, each with different tasks and learning outcomes:

(1) Machine learning research assistant. This role involves extending the functionality of our existing machine learning models. Tasks include training predictive models and testing them on several datasets, organizing new data sources, and working with developers to integrate successful approaches in to the production system. Learning outcomes include familiarization with one or two modern neural network models (e.g., word2vec and recurrent neural networks) and learning how ML can be integrated into a live product.
(2) Front-end / Back-end developer. This role extend the functionality or robustness of the recommender system. Tasks include adding minor feature fixing or improvement in our Angular front end or python back-end. Learning outcomes include familiarization with modern web programming paradigms and exposure to a product development stack including state of the art machine learned models and real-time data streams.

Day-to-day supervisor for this project: Zachary Pardos

Qualifications: Strong python skills and exposure to course materials on machine learning.

Weekly Hours: 6-8 hrs

Off-Campus Research Site: 2121 Berkeley Way
Suite 4209 (Lab)

Related website:
Related website: