NAGALAXMI K

• Gaining expertise in AI/ML development (Data Science and Machine Learning) through training at Scalar Academy

• I built a healthcare chatbot using Langchain to manage conversations, and Faiss as a vector database to quickly retrieve medical information. The chatbot used Retrieval-Augmented Generation (RAG) to provide more accurate and relevant answers to users' healthcare questions. I also created custom prompt templates to guide the chatbot's responses and used Amazon Bedrock to handle Llama 3.1 large language model operations.
• I deployed the chatbot using Streamlit, making it easy for healthcare professionals and patients to use.
• This led to a 40% boost in response accuracy, and user engagement increased by 25%, making the chatbot more reliable.

Tools/Technology: Python, Langchain, Llama 3.1, Amazon Bedrock, Faiss, Streamlit, Docker, AWS, RAG, Chatbots, Prompt Engineering, Healthcare AI, Model Deployment.

• To further my engagement in data science, I've successfully completed a program with ProjectPro during a career break

• Worked at TCS, Bangalore, from June 2008 to October 2018, with an added focus on data science roles from 2015 to 2018.

• Company Overview: The Commonwealth Bank (CBA) is one of Australia's leading financial institutions, with businesses in New Zealand, Asia, and the United Kingdom.
• This project was to perform focused digital marketing by predicting the potential customers who will convert from liability customers to asset customers.
• Conducted data preprocessing and exploratory data analysis (EDA) using the Python libraries Matplotlib, Seaborn.
• Developed predictive models, including Logistic Regression, Support Vector Machine, and Random Forest Classifier.
• Evaluating the models with precision, recall, and AUC metrics, we improved efficiency in identifying potential customers, achieving an impressive AUC score of 0.97 through iterative refinement.
• Conducted a proof of concept to devise and execute automated pipelines for deploying ML models across various environments, utilizing containerization technologies (such as Docker and Kubernetes) and orchestration tools (like Kubeflow) into AWS.
• The Commonwealth Bank (CBA) is one of Australia's leading financial institutions, with businesses in New Zealand, Asia, and the United Kingdom.
• This project was to perform focused digital marketing by predicting the potential customers who will convert from liability customers to asset customers.

Tools/Technology: Python, Numpy, Pandas, Matplotlib, Seaborn, Sklearn, Pickle, Kubernetes, Kubeflow, AWS.

• Company Overview: The Commonwealth Bank (CBA) is one of Australia's leading financial institutions, with businesses in New Zealand, Asia, and the United Kingdom.
• This project aims to predict whether an applicant should receive a loan by building a classification model.
• Data quality was ensured by rectifying missing values, addressing data skewness, and mitigating multicollinearity using Python libraries such as Pandas, Seaborn, and Matplotlib.
• Developed and trained predictive models, such as XGBoost and Random Forest models, to evaluate the risk associated with each loan applicant based on their financial history, credit score, and other relevant features.
• Established Continuous Integration and Delivery (CI/CD): Developed CI/CD pipelines to automate the testing, validation, and deployment of ML models.
• The Commonwealth Bank (CBA) is one of Australia's leading financial institutions, with businesses in New Zealand, Asia, and the United Kingdom.
• This project aims to predict whether an applicant should receive a loan by building a classification model.

Tools/Technology: Python, NumPy, Pandas, Matplotlib, Seaborn, XGBoost, CI/CD, Jenkins.

• Company Overview: Tata Communications Limited, a worldwide leader in telecommunications and digital infrastructure within the Tata Group, focuses on predicting Customer Lifetime Value (CLTV).
• The CLTV metric gauges the total anticipated revenue a customer is likely to generate throughout their association with the company.
• This initiative aims to optimize sales and pricing strategies, enhance customer satisfaction, and mitigate churn rates.
• Performed exploratory data analysis (EDA) to understand the data and identify features that contribute to CLTV based on the aforementioned factors.
• Applied analytics techniques such as outlier detection and quantiles hypothesis testing (One-Sample t-test, Paired Samples t-test).
• Tata Communications Limited, a worldwide leader in telecommunications and digital infrastructure within the Tata Group, focuses on predicting Customer Lifetime Value (CLTV).
• The CLTV metric gauges the total anticipated revenue a customer is likely to generate throughout their association with the company.
• This initiative aims to optimize sales and pricing strategies, enhance customer satisfaction, and mitigate churn rates.

Tools/Technology: Python, NumPy, Pandas, Matplotlib, Seaborn, Scikit-learn, MySQL.