You are on page 1of 2

ArkanathPathak

Computer Science Undergraduate Student

contact Interests

A1-211, LLR Hall
IIT Kharagpur 721302 Algorithms, Machine Learning
West Bengal, India

Education

HD-189, Sector 135
Noida 201301
since 2012
Uttar Pradesh, India
Cell : +91 - 8967024282
pathak.arkanath@gmail.com 2012
arkanath@cse.iitkgp.ernet.in
http://cse.iitkgp.ac.in/~arkanath/ 2010

languages
bilingual Hindi/English

citizenship

Class XII, CBSE
Aggregate Percentage: 88.8
Class X, CBSE
Cumulative Grade: 9.6/10

IIT Kharagpur

St. John’s Senior Secondary School
Lord Mahavira School

Achievements
2013, 2014

Indian

coding handles

B.Tech. student of Computer Science
Cumulative GPA : 9.31/10
Year of Study : Fourth

2009, 2010

Codeforces : arkanath 2010
(top rating: 1932)
TopCoder : arkanath
2011
(top rating: 1329)
CodeChef : arkanath
2012
(top rating: 5784)

Our team qualified the online round of ACM-ICPC Amritapuri
Onsite Rank : 50 in 2013, 32 in 2014
Selected in Regional Mathematical Olympiad
Secured rank 8 in 2010
Awarded with the KVPY Scholarship
Around 200 students selected from all over India
Selected in National Standard Examination in Physics
Around 300 students selected from all over India
Secured a rank of 313 in IIT-JEE
Around 5,00,000 students appeared from all over India

Projects
Improving YouTube personalization using clustering of videos
Internship Location: Google India, Bangalore
Duration: May 4 - July 10, 2015
Description: We explored new ways to improve YouTube user profiles, by trying to find ways of modelling interests that
are not well represented by Knowledge Graph entities (e.g. ”70’s music”). Towards this goal, we used clusters of videos
as a user feature. The input data for the clustering was derived from video correlations due to user co-watches. We
tried various algorithms like HAC, k-means and LDA. We built a simple video recommendation system using clusters as
features. We had to deal with large amounts of input data, and thus, had to use compute clusters for distributing the tasks.
The project, hence, included heavy usage of distributed frameworks, like MapReduce. We also tried ways to generate
cluster descriptors using n-gram language models and video entities. The results looked promising and the team was
interested in carrying forward the approach.
Clustering of mixed data by integrating fuzzy, probabilistic and collaborative clustering framework
People Involved: Prof. Nikhil R. Pal (Project Guide)
Duration: May - June 2014
Description: A new algorithm for clustering data with both numerical and categorical attributes was developed. The
experimental results were competitive with the most famous existing algorithms. We’re working towards a publication.
1

com/) Description: Entertainment website intended to act as a platform for sharing thoughts. Algorithms-I (Grade : 10/10) 11.io/SleekArchive/) Description: PHP-MySQL based note taking application JhonnyM Description: A productivity tool extension for Google Chrome .guesswho15. PHP. Machine Learning (Grade : 10/10) 9. SleekArchive (http://arkanath. JS. Contains database of over 200 thousand quotations and 10 thousand authors. The data was crawled using a custom built JAVA web parser using Jericho library. The app was built using standard IR and AI techniques to suggest semantically similar text. C++. Formal Language and Automata (Grade : 10/10) 13.com/quoteappend) Description: An application integrated with InWordy which suggests contextually similar quotations for a given text. Bootstrap (by Twitter) Framework. Operating Systems (Grade : 10/10) 4. Website Development: • HTML. Skills Programming Languages: • C. GuessWho15 (http://www. MySQL database Design Applications: • Adobe Photoshop. Information Retrieval (Grade : 10/10) 10.github. Probability and Statistics (Grade : 9/10) 12. Discrete Structures (Grade : 10/10) Online Courses: • Machine Learning (Coursera) (Score : 100%) • Algorithms: Design and Analysis. Python Algorithms: • Clustering. Compilers (Grade : 9/10) 3. Algorithms-II (Grade : 10/10) 6. Users can post their own thoughts and like or rate existing content. Database Management Systems (Grade : 10/10) 7. The website is built over the standard LAMP stack. CSS. Part 1 (Coursera) (Score : 97%) 2 .net) Description: A web version of the famous game of guessing a person in 15 turns.Creations InWordy (http://inwordy. Java. Programming and Data Structures (Grade : 10/10) 8. and common algorithms involved in Competitive Programming. Computer Networks (Grade : 10/10) 5. QuoteAppend (http://inwordy. Software Engineering (Grade : 10/10) 2. Cinema 4D and Final Cut Pro X Relevant Courses Taken IIT Kharagpur: 1.