Data Scientist Machine Learning

Reema Naik Desai

Irving, TX 214-***-**** ****************.*****@*****.***

https://github.com/ReeDesai

linkedin.com/in/reema-naik-desai-336154a

Objective

To obtain a challenging data scientist position in a dynamic and innovative organization where I can use my technical and analytical skills.

Experience

AT&T Mobility Sr. Specialist RAN Engineer 2012 – 2020

Helped interpret data like call success rate, accessibility, retainability, signal strength, and data throughput from network monitoring systems effectively.

Identified patterns and anomalies that might indicate network issues or opportunities for improvement.

Learnt customer behavior and market trends using data visualization using python and Tableau.

Data preprocessing, feature engineering, statistical analysis and model building.

Exploratory Data Analysis (EDA) to transform complex data sets into actionable insights. Skills

Programming language: Python (Certified), MATLAB, SQL. Data Visualization: Matplotlib, Seaborn, Tableau.

Education

University of Texas, Post-Grad in Artificial Intelligence & Machine Learning-Business Applications 2024

Major- Machine Learning Minor- Data Science and Statistics San Diego State University, Master’s in Electrical & Computer Engineering 2011 Major: Wireless Telecommunication Minor: Computer Engineering Projects

Restaurant Revenue estimator: Analyzed the data to get a fair idea about the demand of different restaurants which will help food Aggregator Company in enhancing their customer experience.

Decision Tree Model for Personal Loan Targeting: To understand which customer attributes are most significant in driving purchases, and to identify which segment of customers to target more using Decision tree. Model Performance Evaluation and Improvement using pre-pruning (using GridsearchCV) and post- pruning.

Optimizing Credit Card Retention with Advanced Machine Learning Models: Model that will help the bank improve its services so that customers do not renounce their credit cards using 5 models using decision trees, bagging, and boosting methods and performed oversampling and undersampling.

Support Ticket Categorization

Developed a Generative AI application using a Large Language Model (LLM) to automate the classification and processing of support tickets. The application predicts ticket categories, assign priority, suggest estimated resolution time and stores the results in a structured dataframe.

Predicting Customer Churn with Neural Networks

Built a neural network -based classifier that can determine whether bank customer will leave or not in the next 6 months with Adam optimizer and Dropout, SMOTE and SGD optimizer.

Plant Seedling Classification with CNNs

Built a convolutional neural network model which would classify the plant seedlings into their respective 12 categories and evaluate the model on different performance metrics, plot confusion matrix, model performance improvement and final model selection also built a model using data augmentation to overcome data imbalance problem.

Contact this candidate