Skip to content

Charan Bollaram

Junior Data Scientist • India • b********************@gmail.com • +91*******730 • linkedin.com/••••• • github.com/•••••

Career Objective

Results-driven and highly motivated Data Scientist fresher with strong knowledge of Python, SQL, machine learning, deep learning, and data analysis. Skilled in data preprocessing, model building, and deriving actionable insights using Pandas, NumPy, scikit-learn, TensorFlow, and Power BI. Seeking an entry-level Data Scientist role to leverage analytical and problem-solving skills to develop data-driven solutions and support business growth.

Education

St.Martin’s Engineering College
B.Tech • Hyderabad • 2021 – 2025

Technical Skills

Programming Languages: Python,MySQL
Data Analysis & Visualization: Pandas,NumPy,Matplotlib,Seaborn,Power BI,Exploratory Data Analysis (EDA),Data Cleaning,Missing Value Handling,Outlier Detection
Machine Learning: Machine Learning: Supervised Learning,Unsupervised Learning,Logistic Regression,K-Nearest Neighbors (KNN),Random Forest,XGBoost,Feature Engineering,Model Evaluation,Hyperparameter Tuning,Cross Validation,ROC-AUC,F1 Score,Recall Optimization
Deep Learning: Artificial Neural Networks (ANN),Convolutional Neural Networks (CNN),Recurrent Neural Networks (RNN),LSTM,GRU,TensorFlow,Keras
Natural Language Processing & Generative AI:: Natural Language Processing (NLP),Bag of Words (BoW),TF-IDF,NLTK,Transformers,Prompt Engineering,Large Language Models (LLMs),Retrieval-Augmented Generation (RAG),LangChain,Google Gemini API
Data Handling & Analysis:: Pandas,NumPy,Exploratory Data Analysis (EDA),Data Cleaning,Missing Value Handling,Outlier Detection
Visualization & Reporting:: Matplotlib,Seaborn,Power BI
Tools & Platforms:: Streamlit,Jupyter Notebook

Projects

Fake Job Detection using Machine Learning
Tools Used: Python, TF-IDF, Logistic Regression, XGBoost, Random Forest, Naive Bayes, scikit-learn, Streamlit
  • Built an NLP-based fake job detection system on 17,590+ records achieving 95% accuracy using TF-IDF vectorization 3,000+ features and optimized Logistic Regression 1,000 iterations.
  • Evaluated four models (Logistic Regression, Naive Bayes, Random Forest, XGBoost); improved fraud recall from 60% to 85% and obtained ROC-AUC of 0.98 while increasing F1-score by 12%.
  • Developed a hybrid detection approach combining one ML model with four rule-based checks to boost real-world detection by 10–12% and deployed a Streamlit app supporting 100+ predictions per session with probability visualizations.
Flipkart Sentiment Analysis
Tools Used: Python, TF-IDF, Logistic Regression, NLP, Streamlit
  • Developed an NLP sentiment analysis pipeline trained on 10,000 Flipkart product reviews achieving 88–90% accuracy using TF-IDF and Logistic Regression.
  • Implemented end-to-end text preprocessing tokenization, stopword removal, lemmatization that reduced irrelevant features by ~30% and improved classification performance by 12%.
  • Deployed the model as an interactive Streamlit web application enabling sub-second responses and supporting 100+ user inputs per session for real-time sentiment predictions.
Financial Advisor GenAI Chatbot
Tools Used: Google Gemini API, Prompt Engineering, Conversational Memory, Streamlit
  • Built an AI-powered Financial Advisor Chatbot using Google Gemini API to deliver personalized investment guidance based on user risk profiles and goals.
  • Implemented conversational memory and dynamic prompt engineering to improve contextual relevance in multi-turn advisory interactions.
  • Created an interactive dashboard to visualize real-time AI recommendations and deliver personalized investment insights to users.

Certifications

Python — HackerRank
My-SQL — Innomatics Research Labs
Machine-Learning — Innomatics Research Labs
GenAI-Internship — Innomatics Research Labs

Powered by Drivetube · Create your own profile at drivetube.ai