Hi there!
I am Kiran Kannar, and I currently work as a Software Engineer (MTS) at Salesforce in the Field Service team.
I am deeply motivated by human behavioural modelling; I like to understand and study how we interact with each other, and how this behaviour transpires in online communities and social networks. My Master's thesis at University of California, San Diego (UCSD) was in modelling sequential dynamics in recommender systems and exploiting temporal and geographical rhythms in human mobility.
I graduated with a Master's degree in Computer Science at UCSD in June 2018. I wrote about some of my grad school experiences on Grad School Musings on Medium.
Some of my broad interests are in machine learning, deep learning, and recommender systems. I am open to a wide variety of research in these areas.
Previously, I worked as a Software Engineer for Oracle at Bengaluru.
I completed my Bachelor's degree in Computer Science at R.V. College of Engineering in 2014.
In my free time, I write short stories, some of which end up on FreeThinker. I also blog about my graduate school experience on Medium.
I love football and I am a Gooner for life.
Contact details: kirankannarkk(dot)lris(at)gmail(dot)com
Master's thesis under Prof. Julian McAuley on sequential recommender systems. I worked with metric embeddings to model user-item and item-item interactions in one metric space and incorporated various techniques to model temporal and geographical behavioural rhythms in human mobility.
Modelling of user listening behaviour on Spotify and Last.fm by modelling song sequences in 30Music and NowPlaying datasets. We empirically prove the effectiveness of metric embeddings over matrix factorization and factorized markov chain models and suitably extend the embedding model.
Using a latent factor model to model the evolution of user expertise by fitting a recommender system for each level of expertise. Project reproduces the results obtained in the main paper
Working in the Field Service team of Service Cloud product
Worked in the Field Service team of Service Cloud product
Developed Entity Milestones Tracker Component for Lightning UI
Worked in the Core team of PeopleTools, Oracle PeopleSoft.
Point of Contact of Accessibility Compliance for PeopleTools IDC
Interned and completed my final year project here.
Worked on building a Scalable Query Framework for near-real-time responses.
Implemented Bayesian Personalized Ranking (BPR-MF) for restaurant recommendation using Las Vegas data extracted from the Yelp Round 9 Dataset challenge.
Implemented Quora’s LSTM with concatenation architecture to model semantic similarity detection in classifying question pairs as duplicate or not. Experimented with various deep networks and word embeddings.
Predicted the number of helpfulness votes for a product review using regression, and the product rating using matrix factorization as a part of Kaggle competition in CSE 258 - Web Mining and Recommender Systems
Review paper for CSE 291 - Convex Optimization analyzing various algorithms in Online Convex Optimization and Bandit Convex Optimization, and the seminal work on algorithms that promise tighter bounds for regret functions in bandit setting.
Built within PayPal’s data analytics platform using HBase and Elasticsearch to provide near-real time responses to queries over terabytes of PayPal user clickstream data.
Built a visualization system using D3.JS, NodeJS and AngularJS to interface with Druid data-store, with the provision of OLAP operations
One of 6 teaching assistants for the undergraduate class under Prof. Miles Jones
Course website:
CSE 21
One of 5 teaching assistants for a undergraduate class under Prof. Andrew Kahng.
Course website:
CSE 101
One of 5 teaching assistants for a graduate class of 187 students under Prof. Ramamohan Paturi.
Course website:
CSE 202
One of 4 teaching assistants for an undergraduate class of 134 students under Prof. Yannis Papakonstantinou
Course website:
CSE 135
