Karishma A. Borse
**, *** ****** **** #****, San Jose, California, 95134 · 913-***-****
adb2eo@r.postjobfree.com
https://www.linkedin.com/in/karishma-borse-333b6430/
https://github.com/karishmaborse?tab=repositories
Objective: Seeking for Data Analyst Intern role.
Education:
MS, University of Central Missouri, Big Data Analytics, December 2020, GPA 3.8
MBA, University of Mumbai, Operations Management, June 2016, GPA 3.82
B.E, University of Mumbai, Information Technology, June 2014, GPA 3.2
Technical Skills:
Programing languages: Python, Java, R, Scripting language – SQL/ MySQL
Machine Learning: Regression, Classification, Clustering
Deep Learning: ANN, CNN, PCA, XGBoost, LDA
Web Technologies: Flask, Django, Bootstrap, Java Script, HTML/CSS.
Cloud Technologies: AWS SageMaker.
Big Data Technologies: PySpark, Apache Hadoop, Hive.
Databases: MongoDB, MySQL, SQL Alchemy, SQLite.
Libraries: Numpy, SkiLearn, Tensorflow, Pytorch, Pandas, Matplotlib.
Analytics Tools: Tableau, Google Analytics, MS-Excel Advance.
Projects:
Green House Gases contribution to Global Warming:
Trained a machine learning model using Python with the Numpy library to predict the future rise in global warming using regression technique.
Developed webpages using JavaScript and Bootstrap templates to showcase the outcomes, for connection used Python Flask used datasets from Kaggle and from NASA free APIs.
For feature selection and information visualization used Tableau.
Future Diabetic Patients Predictions
Data processing by replacing missing values with the mean of the patient’s data sets, using matplotlib library feature selection using Python.
Used Multiple Linear Regression to predict among the patient’s dataset, who is more susceptible to Type1, Type 2 diabetes.
To analyze the accuracy of the model Confusion Matrix.
Effectively used Sigmoid and Relu as deep learning functions for feature scaling.
How Much Millennial’s will Spend on Food Trends, Predictive Analysis
Data collected from APIs in the form of JSON format and Kaggle datasets, Used OneHotEncoder,LabelEncoder classes of the Numpy for creating dummy variables of the categorical variables.
Trained the model using Multiple Linear Regression using machine learning library like SkLearn.
Data retrieved from MongoDB database and made a successful connection.
Experience:
Management Intern, Axis Bank, Apr- Aug 2015
Assisted to design a model which will solve the stock outs of ATM machines which has accuracy about 95%.
Analyzed the data collected from market research to improve the efficiency of the model designed for ATM machines. Used Tableau for Information Visualization and Finacle software for the data mining.
Relevant Courses:
Business Intelligence Analytics
Learning about various machine learning algorithms as well as AWS SageMaker for analytics.
Big Data Architecture
Learned about architecture and applications of Hadoop, Spark, Hive, Map Reduce.
Big Data Solutions for Business
Learned about MongoDb, various libraries of R for analysis. Relational database like MySQL connections for data flow.