Ritika Joshi, MS(IS), B.Tech (ECE)
Data Scientist, adcm8h@r.postjobfree.com, 818-***-****, LinkedIn, Los Angeles, CA
SUMMARY
Highly motivated, detail oriented technology professional with cumulative 7 years of experience in tech. development, data science and ML project management under web, finance and networking domains.
TECHNICAL SKILLS
Operating Systems
UNIX, Linux, MS Windows
Programming Languages
Python, pySpark, C, C++, Shell Scripting, Socket Programming
Database
Sybase, MySQL
ML Tools
Azure ML Studio, Databricks, Spark
ML Libraries
pandas, numpy, seaborn, matplotlib, scikit, Gensim, NLTK
Data Analytics Tools
Tableau, SAS Studio, SAS Visual Analytics, Power BI, Hadoop, Hive, Apache Pig
Programming Tools
Putty, Visual Studio, CyberArk, Autosys, Jupyter notebook, Anaconda
Management Tools
JIRA, ServiceNow, Trello, MS Project, MS Excel, MS Word, Confluence, GitLab
PROJECTS
Technical Project Manager (Intern)
Internet Brands, Los Angeles Oct’19-Current
·Developed a ML model to analyze all reviews for a given apartment and to generate snippets that represents the most frequent topic or theme for that apartment.
·Built LDA model to classify reviews using unsupervised approach and used the topics generated from LDA model as features to do the supervised classification.
·Used Pseudo labelling approach to improve the results of classification.
·Applied NLP techniques to clean the text reviews.
·Libraries used Scikit, Gensim, NLTK, Spacy, Pandas and database used - MySQL
Data Scientist Dec’18-May19
California State University, CA
Predictive model on Breast Cancer
·Developed a supervised classification machine learning model to predict breast cancer using classification algorithm.
·Pre-processed data using pandas and numpy lib, visualizations created using matplotlib, seaborn lib and ML model created using scikit, sklearn pandas_ml lib.
Obesity Risk Prediction
·Developed a model to monitor priority health risk behaviors that contribute markedly to the leading causes of death, disability, and social problems in the United States.
·Worked on pySpark in Databricks to build model and to find out the model accuracy.
·Used AzureML to develop model prototype on smaller set of data.
·Testing and training done using Linear Regression, Decision Tree Regression algorithms.
·GitHub Link: https://github.com/rjoshi5/Obesity-Risk-Level-Among-Youth
BNP Paribas, Mumbai, India Sep’15 – Nov’17
Support Analyst
·Developed monthly statistic reports using python to analyze system issues and plan system upgrades.
·Developed python scripts for the automation purposes and performed application releases and disaster recovery activities. Database used - sybase.
Wipro Ltd, Mumbai, India Jun’14 – Sep’15 Project Engineer
·Developed python scripts for the automation purposes and developed system reports using SQL.
·Wrote C++ and assembly modules to implement features to existing services and to extend capabilities of the soft switch.
PROFESSIONAL DEVELOPMENT
·Lynda: Python3 Essential training
·Lynda: Programming Foundations: Object-Oriented Design (2012)
References available on request