Programming/Data Analysis
Python, Java, JavaScript,,
PostgreSQL, PySpark, SQL
Tools and Software
Keras, TensorFlow, PyTorch,
Scikit, NLTK
Natural Language
Programming-
Genius, NLTK, Tweepy, Scikit
Machine Learning-
Seaborn, Pandas, NumPy, PIL,
OpenCV, Time Series
Analysis, matplotlib, ANN
Statistics and Probability-
Regression, classification,
Bayes Theorem
PROFESSIONAL EXPERIENCE
As a result-oriented professional in Data Science, experience with Statistical Data Analysis, Machine Learning, Deep Learning, Artificial Neural Network and NLP using TensorFlow, Keras, and Scikit-learn; strong background of Python (NumPy, Pandas, Matplotlib, Seaborn, etc) and SQL development (Oracle, MySQL, and PostgressDB); looking for a challenging role in the Data Science field. GRADUATE RESEARCH ASSISTANT
California state university/Fullerton, CA/ July 2019-Present
• Developing brain-inspired multimodal using intersection of computer vision and Natural language processing (NLP) algorithms.
• Extracted features from EEG data and mapped it into Gaussian distribution, developed encoder and decoder using deep learning algorithms CNN, LSTM, and GAN for object generation. Developed Artificial Neural Network(ANN) for encoding the data. JUNIOR DATA SCIENTIST
Tata consultancy Services / Brussels, Belgium / Aug 2016-Dec 2018
• Performed data pre-processing and manipulation on the EMEA Tax dataset comprising of structured, semi-structured and unstructured data.
• Used Logistic Regression and Discriminant Analysis for data categorization into groups of sectors and machine learning algorithms like Linear Regularized Regression, Decision Trees, Random Forest and XGBoost for quantitative estimation.
• Initiated implementation of automated data level security tools using Python and JavaScript. Used NLTK to pre-process the summary and resolution of security tickets. Appreciated by a client for same
DATA ENGINEER
Tata consultancy Services / Mumbai, India / Dec 2010-Aug 2016
• Analysed business processes identified automation opportunities, re-engineered process to improve project potential and strategy.
• Developed and tested ETL pipelines for data migration from Oracle to SAP HANA
• Performed SQL-code optimization and designed stored procedures on incremental data.
• Automated database health-check operation with Python, Unix Scripting, PLSQL, and HTML. SECRETARY
Bright Spot LTD / Boston, MA / Jun 2007-Aug 2008
• Typed documents such as correspondence, drafts, memos, and emails, and prepared 3 reports weekly for management.
Kaggle- Text mining- Happy DB
• Used Latent Dirichlet Allocation (LDA) model to explore the causes that makes people happy, combined with word cloud, stacked area graph, heatmap, bigrams, etc.
• Used text2vec package to construct a document-term matrix (DTM) from text corpus Text Summarization for web scraped content
• Devised various abstractive and extractive algorithms using NLP that summarized long news articles in Python. Implemented a Hidden Markov Model that judges the likelihood of each sentence for being in the summary
Kaggle - Sentimental analysis of product review
• Using NLP tool kit, Scikit-learn and algorithms like KNN, LSTM-Word2Vec, LSTM-Glove perform product review of amazon product review dataset and achieved 95% accuracy Prediction of customer retention and Article popularity
• Classified Bank marketing promotion drive data to predict long-term deposits by customers and Online news dataset to predict popularity of an article
• Performed data cleaning, data analysis by using SVM, KNN, Random forest, Naïve Bayes logistic regression AI achieved F1 score of 0.87 and 0.67 respectively Radar Signal Analysis
• Implemented Java based Radar signal analysis model with Java open source and deep learning neural networks.
• Model denoise input radar signal with JWave and analysed it with the LSTM algorithm. Music Music Recommendation
• Built interactive Music recommendation website to generate and play songs for a customer. Used NLTK for word tagging and keyword selection
• Key skills: Exploratory Data analysis, NLTK, popularity-based filtering, collaborative based filtering
RELEVANT PROJECTS
IEEE PUBLICATION
MASTER OF COMPUTER
ENGINEERING
GPA 3.9, expected - Dec
2020
California State University,
Fullerton
Received the award of the
department scholarship
Relevant Coursework:
Machine Learning, Advanced
Database Management
BACHELOR OF COMPUTER
SCIENCE
GPA 3.9, June 2010
Mumbai University, India
Relevant Courses –
Data structures and
Algorithms, Object Oriented
Programming, Database
Systems, Operating System
ADDITIONAL SKILLS
EDUCATION
CERTIFICATIONS
RUCHI BAGWE adcg7u@r.postjobfree.com
Automated Radar Signal Analysis Based on Deep Learning JAN 2020 Published in IEEE CCWC – ISBN -978-1-7281-3783-4
• Neural Networks and Deep
Learning by deeplearning.ai
• The Data Scientist’s
Toolbox by Johns Hopkins
University