Scribd Logo
Upload

Welcome to Scribd!

  • 50 views

    Himanshu Sharma: Projects Tech Stack

    Uploaded by

    Nitish
    This document provides a summary of Himanshu Sharma's skills and experience. It includes details of several projects he has worked on related to recommendation systems, predictive modeling, and computer vision. His technical skills include Python, C, PHP, MySQL, Scikit-learn, Keras, Pandas, and OpenCV. He has a B.Tech in Computer Science from Presidency University with a CGPA of 9.24.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Himanshu Sharma: Projects Tech Stack

    Uploaded by

    Nitish
    50 views1 page
    This document provides a summary of Himanshu Sharma's skills and experience. It includes details of several projects he has worked on related to recommendation systems, predictive modeling, and computer vision. His technical skills include Python, C, PHP, MySQL, Scikit-learn, Keras, Pandas, and OpenCV. He has a B.Tech in Computer Science from Presidency University with a CGPA of 9.24.

    Original Title

    Resume HimanshuSharma

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document provides a summary of Himanshu Sharma's skills and experience. It includes details of several projects he has worked on related to recommendation systems, predictive modeling, and computer vision. His technical skills include Python, C, PHP, MySQL, Scikit-learn, Keras, Pandas, and OpenCV. He has a B.Tech in Computer Science from Presidency University with a CGPA of 9.24.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    50 views1 page

    Himanshu Sharma: Projects Tech Stack

    Uploaded by

    Nitish
    This document provides a summary of Himanshu Sharma's skills and experience. It includes details of several projects he has worked on related to recommendation systems, predictive modeling, and computer vision. His technical skills include Python, C, PHP, MySQL, Scikit-learn, Keras, Pandas, and OpenCV. He has a B.Tech in Computer Science from Presidency University with a CGPA of 9.24.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 1

    Himanshu Sharma

    Data Scientist | Bengaluru

    [email protected] +91-7354966990 linkedin.com/in/himan-10 github.com/Harsh1091996

    PROJECTS TECH STACK


    Amazon Book Recommendation Framework Languages
    Python, C, PHP, MySQL
    AlmaBetter Verified Project
    04/2021 - 05/2021,
    Frameworks
    Tags: Word2Vec, Content-based Filtering, Collaborative Filtering, Cold start problem, Top-N metrics
    Scikit-learn, Keras, Pandas, Numpy, Matplotlib,
    Developed a book recommendation system for amazon customers using memory and OpenCV, NLTK, Plotly, Flask
    model based collaborative filtering by utilizing the book description and user interests.
    U s e d Word2Vec vectorizer on descriptions to obtain user-item interactions and Platforms
    employed cosine similarity to measure user-item and item-item similarities.
    Jupyter Notebook, Tableau, Git Version Control,
    Created profiles for top active users by leveraging interaction strength with the PostgreSQL, Spyder, Terminal, PyCharm
    recommended items and achieved test MAP@5 of 42% and MAP@10 of 53%.
    Handled the cold start problem based on global and demographic-specific book
    popularity and improved the efficiency of the user recommendation engine by 33% .
    RELEVANT COURSEWORK
    Email Campaign Creative Effectiveness Python for Data Science and Machine Learning
    AlmaBetter Verified Project (Udemy) (09/2020 - 10/2020)
    EDA, Linear/Logistic Regression , SVM, KNN, Decision Tree,
    02/2021 - 03/2021, Random Forest, K Means, NLP, Neural Networks
    Tags: Classification, KS Statistic, Gains table, SMOTE, Hyperparameter Tuning, Model Interpretability
    Developed multi-class XGBoost model to characterize the email creative and predicted
    its effectiveness that is ignored, read, acknowledged by the reader.
    Performed missing value imputation using KNN-Imputer, implemented SMOTE PUBLICATIONS
    boosting, and carried out hyperparameter tuning using Bayesian Optimization.
    Medium
    Leveraged SHAP plots to identify key model drivers such as limit of word count, Blogs on Data Science
    keywords, campaign type, communication time, and personalization. 2021
    Obtained F1 scores of 89% & 84% on train and test data respectively and estimated an Natural Language Processing (NLP), Hierarchical
    overall increase in the customer acquisition rate by 15%. Clustering, Regularization

    YouTube
    News Popularity Prediction
    Vlogs on Data Science
    AlmaBetter Verified Project 2021
    12/2020 - 01/2021, Unsupervised Learning Algorithms, Advanced
    Tags : Regression, NLP, TF-IDF Vectorizer, Random Search, XGBoost, Goodness of Fit, spaCy Machine Learning
    Built an XGBoost regression model to predict the popularity of news on different social
    media platforms such as Facebook, LinkedIn and Google Plus.
    Performed key NLP processing steps on news items such as lemmatization, POS-
    tagging, Named Entity Recognition, stopword removal and tokenization using spaCy. EDUCATION
    Generated the optimal document-word matrix as model input by tuning parameters
    such as min_df, max_df, n_gram range, token_pattern in TF-IDF vectorizer.
    B.Tech in Computer Science & Engg
    Performed hyperparameter tuning using GridsearchCV & RandomSearchCV and
    Presidency University, Bengaluru
    achieved R2 score of 72%, 76%, 78% respectively for FB, LinkedIn & GooglePlus. 2016 - 2020,
    CGPA - 9.24

    Face Recognition Attendance System


    Presidency University Verified Project XII-Higher Secondary
    02/2020 - 05/2020, The Sapphire School, Ratlam
    Tags : Face Recognition, Deep Learning, Image Processing, OpenCV, Flask, Raspberry Pi, SQLite 2016,
    Built an IoT-enabled Web app using Python, Flask a n d Sqlite where students can Percentage - 67.0%
    register themself and faculties can sign in and initialize the attendance process.
    Encoded a picture using the HOG algorithm to create a simplified version of the image.
    Found the part of the image that most looks like a generic HOG encoding of a face. X - Secondary
    Passed the centered face image through a Deep Convolutional Neural Network that Ratlam Public School, Ratlam
    knows how to measure features of the face and saved those 128 measurements. 2013,
    Developed an SVM classifier to find the person in our database of known people who CGPA - 7.0
    has the closest measurements to our test image.
    Obtained an accuracy of 99.8% and able to deliver accurate face recognition
    attendance system with minimal human intervention , less time consuming compared to
    manual attendance system and reduced discrepancies like proxy attendance . ACHIEVEMENTS
    Best Paper Award for paper titled Face
    Recognition Based Attendance System (FRAS)
    at Presidency University, 2019

    You might also like