Scribd Logo
Upload

Welcome to Scribd!

  • 6 views

    Hemant Kumar Jha: Education

    Uploaded by

    deletem521
    Resume

    Copyright:

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

    Hemant Kumar Jha: Education

    Uploaded by

    deletem521
    6 views1 page
    Resume

    Original Title

    r3f

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Resume

    Copyright:

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

    Hemant Kumar Jha: Education

    Uploaded by

    deletem521
    Resume

    Copyright:

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

    HEMANT KUMAR JHA

    Github | LinkedIn | [email protected] | +91 9631580629

    EDUCATION
    Lakshmi Narain College of Technology Nov-2021 – Jun-2025
    Bachelor of Technology, Computer Science, CGPA-7.78
    Courses: Operating System, Data Structures, Analysis and Algorithms, Database Management System, Computer Networks

    SKILLS
    Programming: Python, Data Structures and Algorithms, Object Oriented Programming
    Machine Learning: Exploratory Data analysis, Feature Engineering, Regressions
    Deep Learning: Artificial Neural Networks, Convolution Neural Networks, Recurrent Neural Networks, LSTMs, GRUs

    EXPERIENCE
    FORAGE MACHINE LEARNING VIRTUAL INTERNSHIP
    • Gained comprehensive understanding of the entire Machine Learning development lifecycle, including the creation of data
    diagrams to illustrate workflow phases.
    • Conducted Exploratory Data Analysis (EDA) on a dataset of 10000 records using Pandas, Matplotlib, and Seaborn to
    visualize data distributions, correlations, and trends, identifying significant patterns in job satisfaction, and departmental
    turnover rates.
    • Applied cross-validation techniques, improving model robustness and generalizability, resulting in a 10% reduction in
    prediction error across different data subsets.

    PROJECTS
    TIME SERIES ESTIMATION
    • Created a LSTM-based model to predict stock prices based on historical data, achieving a Mean Absolute Error (MAE) of 3%
    on a test dataset.
    • Built and trained the LSTM model using TensorFlow and Keras, optimizing hyperparameters such as the number of LSTM units,
    learning rate, and batch size to improve prediction accuracy.
    • Executed a sliding window approach for sequence data processing and prediction, capturing temporal dependencies in stock price
    movements.
    • Evaluated model performance using metrics such as MAE, Mean Squared Error (MSE), and Root Mean Squared Error (RMSE),
    ensuring robustness and reliability in predictions.

    EMPLOYEEE CHURN PREDICTON


    • Constructed a machine learning model to predict employee churn rate based on features such as job satisfaction, performance
    ratings, and work-life balance, achieving an accuracy of 87%.
    • Conducted comprehensive EDA, including handling missing values, encoding categorical variables, and scaling numerical
    features, using Python libraries such as Pandas and Scikit-learn.
    • Applied Principal Component Analysis (PCA) to reduce the dimensionality of a high-dimensional dataset, retaining 95% of the
    variance in the data while reducing the feature set by 60%.

    MOVIE RECOMMENDATION SYSTEM


    • Merged and cleaned TMDB Movies and Credits datasets, handling missing values and duplicates, and transformed JSON-like
    strings into structured lists for genres, keywords, cast, and crew.
    • Created a 'tags' feature by combining genres, keywords, cast, and crew attributes, applied Tokenization and Stemming, and
    used CountVectorizer to convert text data into numerical vectors.
    • Calculated Cosine Similarity between movie vectors to measure similarity, implemented a recommendation system to suggest
    similar movies, and ensured accuracy through manual inspection and validation.
    • Utilized Python, pandas, NLTK, and sklearn libraries, demonstrating proficiency in data manipulation, Natural Language
    Processing, and machine learning to build an effective movie recommendation system.

    You might also like