Jishnu Bhattacharyya

Jishnu Bhattacharyya

United States
500+ connections

Join to view profile

About

Data Science is the art of deriving key insights that drive business decisions.
I…

Activity

Experience

  • Aetna, a CVS Health Company Graphic

    Aetna, a CVS Health Company

  • -

  • -

    Greater Philadelphia Area

  • -

  • -

    Buffalo Grove, Illinois

  • -

    Samalkha, India

  • -

    Bengaluru Area, India

  • -

    Gurgaon, India

  • -

    Noida Area, India

Education

Licenses & Certifications

Patents

Courses

  • Advanced Database Systems

    -

  • Analysis of Categorical Data

    -

  • Applied Regression Analysis

    -

  • Human-Computer Interaction and User Interface Technology

    -

  • Introduction to Data Mining

    -

  • Introduction to Machine Learning

    -

  • Machine Learning

    -

  • Principles of Database Systems

    -

  • Social Network Analysis

    -

Projects

  • Optimizing Player Performance in ‘League of Legends’, a multiplayer online battle arena video game

    - Present

    ▪ Collaborated with Riot Games to implement a model to recommend suitable champion or role to optimize player performance
    ▪ Developed a correlation model to establish temporal causality of various types of game event interactions
    ▪ Delivered a performance improvement of 20% over baseline model on approximately 65 GB of data

  • FP-Growth Algorithm

    ▪ Used Java to design a method to build an FP-Tree for the given transactions
    ▪ Implemented the FP-Growth algorithm to generate frequent itemsets by dynamically generating conditional FP-trees
    ▪ Generated frequent association rules from the frequent itemsets by dynamically using the Apriori algorithm

  • Image Style Transfer

    -

    Used pre-trained Convolutional Neural Network VGG19 to transform the base image such that it closely matches the content and style images by minimizing the content and style losses with backpropagation

  • Modeling and Predicting Influence using Hypergraphs in a Social Network

    -

    ▪ Used Python on DBLP dataset to detect directed hyperedges using hypergraphs instead of dyadic graphs, to capture group properties, where the head and tail of the edge refers to the influencer and the influenced of a collaboration respectively
    ▪ Produced realistic inferences groundwork for influence prediction in the future given the probabilities of influence of hyperedges

  • Classification

    -

    ▪ Used Java to implement K-Nearest-Neighbor classification and Ridge Regression classification
    ▪ Performed model selection by finding the best performing parameters for the algorithms using the validation set

  • Clustering

    -

    ▪ Used Python to preprocess articles to generate sparse high dimensional vectors by performing tokenization
    ▪ Used Java to implement K-means, Spherical K-means and an external criterion based clustering on these vectors
    ▪ Designed and delivered high performing algorithms assessed on the basis of entropy and purity

Languages

  • English

    Full professional proficiency

  • Hindi

    Native or bilingual proficiency

  • Bengali

    Native or bilingual proficiency

  • Spanish

    Elementary proficiency

  • Punjabi

    Elementary proficiency

Recommendations received

2 people have recommended Jishnu

Join now to view

View Jishnu’s full profile

  • See who you know in common
  • Get introduced
  • Contact Jishnu directly
Join to view full profile

Other similar profiles

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Others named Jishnu Bhattacharyya

12 others named Jishnu Bhattacharyya are on LinkedIn

See others named Jishnu Bhattacharyya

Add new skills with these courses

See all courses