Summary
Overview
Work History
Education
Skills
Projects
Disclaimer
Timeline
Generic

Poonam B.

Data Scientist
Pune

Summary

Data Scientist with a strong focus on managing complex datasets for machine learning applications. Proficient in natural language processing and a wide array of machine learning algorithms, with a keen ability to visualize and analyze data to uncover actionable insights.

Overview

2025
2025
years of professional experience
3
3
Languages

Work History

Data Scientist

Datametica
9 2020 - Current
  • Expertly manage and analyze large datasets, employing advanced data manipulation techniques for machine learning projects
  • Transform raw text into actionable features using natural language processing (NLP) tools for machine learning applications
  • Implement a wide range of machine learning algorithms, including Logistic Regression, Naïve Bayes, k-NN, Support Vector Machine, Decision Tree, Random Forest, and more
  • Leverage Python libraries such as Scikit Learn, Pandas, NumPy, Matplotlib, and Seaborn for efficient algorithm implementation
  • Utilize advanced text processing frameworks like NLTK, TF-IDF, Word2Vec, and others for comprehensive NLP tasks
  • Apply deep learning techniques, including Neural Networks and CNNs, using TensorFlow and Keras
  • Create insightful visual data narratives using Matplotlib and Seaborn to effectively communicate findings
  • Enhance model performance through robust data preprocessing and effective feature engineering
  • Apply machine learning solutions to real-world problems with a focus on structured model evaluation and hyperparameter tuning

Education

Master of Business Administration -

Pune University

Skills

    Programming Languages: Python

    Machine Learning Techniques: Decision Tree, SVM, Linear Regression, Ridge Regression, Lasso Regression, Logistic, KNN Regression, Random Forest, Naïve Bayes, K Means, Ensemble Techniques PCA, AdaBoost Grid Search CV, Random Search CV, Hypothesis testing, Predictive modelling

    Python /ML Packages: Pandas, NumPy, Scikit learn

    Natural Language Processing: Understanding, representation, classification & clustering nltk, Genism , text blob, lang detect, google trans ,BOW, TFIDF, word2vec, doc2vec,sent2vec ,key phrase extraction

    Data Visualization: Matplotlib, Seaborn,

    Database: SQL, MYSQL

    Deep Learning: Neural Networks, Deep Learning, ANN, CNN, RNN, Back Propagation, Transfer Learning, TensorFlow 2x, Kera’s

    Cloud Platform Services & Deployment: AWS, Flask, Postman

    Version Control: GitHub, Git Bash

Projects

Project 1: Automated Document Verification System

Domain: Insurance

· Design and develop deep learning models for document verification, such as Optical Character Recognition (OCR), image classification, or anomaly detection models.

· Applied comprehensive data preprocessing methods, including image resizing for uniformity and normalization of pixel values.

· Employed data augmentation methods to enhance dataset variety and improve model adaptability.

· Optimize model performance for speed and accuracy.

· Committed to professional development by engaging in current front-end trends and technologies.

____________________________________________


Project 2: Sentiment Analysis of Organic Products.

Domain: Retail

· Developed and implemented a custom NLP-based sentiment analysis model to classify customer feedback on organic products into positive, neutral, or negative  categories.

· Collaborated with cross-functional teams to define project goals, acquire and preprocess data from multiple sources, including product reviews, social media comments, and customer surveys.

· Conducted extensive data cleaning and text preprocessing, including tokenization, lemmatization, removal of stopwords and feature extraction.

· Applied machine learning algorithms to build robust sentiment classifiers and Optimized model performance using hyperparameter tuning and cross-validation.

· Worked with Data Engineers to build automated data pipelines, ensuring continuous collection and analysis of customer feedback.

· Presented project outcomes to stakeholders, demonstrating how sentiment trends informed product development in the organic product market.

____________________________________________


Project 3: Bank Marketing Campaign Optimization

Domain: Banking Financial Services

  • Developed predictive models to improve the targeting and effectiveness of bank marketing campaigns, focusing on customer engagement and conversion rates.
  • Collected and cleaned large datasets from multiple sources, including customer demographics, transaction history, and previous campaign responses, ensuring high data quality for model training.
  • Thoroughly processed and cleansed data to rectify missing elements and eliminate outliers
  • Executed detailed exploratory data analysis (EDA) to derive meaningful insights from data.
  • Implemented machine learning algorithms to predict customer response to marketing campaigns and critically assessed model performance using metrics.
  • Performed cross-validation and hyperparameter tuning to optimize model performance, reducing false positives and improving precision in customer targeting.
  • Collaborated with marketing and operations teams to automate the deployment of predictive models, ensuring real-time analytics for ongoing campaigns.

Disclaimer

I affirm that the information provided above is accurate and reflects my true knowledge and belief.

Timeline

Data Scientist

Datametica
9 2020 - Current

Master of Business Administration -

Pune University

Similar Profiles

CREATE PROFILE
Poonam B.Data Scientist