Sara Shaikh
Verified Data Scientist
Data Scientist
Sara Shaikh is an experienced data scientist with over 6 years of expertise in machine learning, deep learning, NLP, computer vision, and time series analysis. She has successfully led data science teams, working on diverse projects in industries such as HR analytics, supply chain, and AI-driven chatbot solutions. Skilled in Python, R, and various ML frameworks like TensorFlow and PyTorch, Sara is proficient in building and deploying models to deliver impactful business insights. She has experience working with renowned companies such as Capgemini and HP Inc., leveraging technologies like GPT-3.5, BERT, and Azure Machine Learning to enhance operational efficiency and data accuracy.
PREVIOUSLY AT
T-Mobile
LOCATION
Hyderabad, India
AVAILABILITY
Full-time
Skills
Azure Open AI
BERT
C++
Data Science
Jupyter
KNN
Microsoft Azure ML
Microsoft Azure Studio
MS SQL
PowerBI
Python
Work Experience
Lead Data Scientist
Capgemini
2023-2024
- Developed AI-driven Q&A chatbot systems using GPT-3.5 for efficient data extraction.
- Automated business processes using Power Automate and optimized workflows with Azure Machine Learning.
- Built financial report summarization systems with GPT-3.5 Turbo and Streamlit, enhancing data processing accuracy.
TECHNOLOGIES
Python, Streamlit, GPT-3.5, BERT, Claude model, CatBoost, Logistic Regression, KNN, K-means, Decision Trees, Random Forest, Azure Machine Learning Studio, Azure Open AI, Power Automate, Azure Cloud Storage, GPT-3.5, Claude model, Azure Cloud Storage, Jupyter, Streamlit, Power Automate
Lead Data Scientist
T-mobile
2023 - 2024
- Developed a machine learning model (CatBoost) for predicting employee attrition.
- Applied sentiment analysis using BERT and Flant5 to predict employee retention.
TECHNOLOGIES
Python, Jupyter, CatBoost, Logistic Regression, KNN, K-means, Decision Trees, Random Forest, LSTM, BERT, Flant5, Streamlit
Senior Data Scientist
HP Inc
2022
- Created demand forecasting models using ARIMA, LSTM, and DARTS for supply chain optimization.
- Implemented precise sales forecasts across multiple markets, improving business decision-making
TECHNOLOGIES
Python, Flask, ARMA, ARIMA, ARIMAX, SARIMA, SARIMAX, LSTM, DARTS, RNN, MAPE, Jupyter Notebook, Flask Framework
Data Scientist
Starbucks
2019
- Developed a machine learning-based demand forecasting model covering over 400 stores and 500 stock-keeping units (SKUs).
- Used Prophet, Random Forest, and LightGBM to build an ensemble model for accurate demand forecasting.
- Trained models using time-series data, analyzing the impact of factors like holidays, promotions, and events on demand forecasts.
- Profiled and disaggregated daily demand from weekly forecasts for various product categories.
- Evaluated model performance and made necessary adjustments to improve forecast accuracy.
TECHNOLOGIES
Python, Jupyter, Prophet, Random Forest, LightGBM, Time-Series Data Forecasting, Meta-Learning, Ensemble Models
Data Scientist
L'Oreal India
2018
- Implemented end-to-end demand forecasting and sensing pipelines for Loreal’s eCommerce and offline channels.
- Optimized the supply chain by integrating forecasting with inventory management.
- Created forecasts for new product introductions by identifying key features and using machine learning models.
- Utilized Sktime, DARTS, and Pyflux to predict demand for products across different channels.
TECHNOLOGIES
Python, Jupyter, Sktime, DARTS, Pyflux, Jupyter Notebook
Data Scientist
Oracle
2018
- Developed a model to extract skill sets from a resume repository and generate profile summaries based on skillset, experience, and projects.
- Scored resumes by analyzing extracted information to provide precise profile assessments.
- Utilized NLP and LinkedIn Scraper (Phantombuster) to gather and process relevant data from resumes.
- Streamlined resume scoring and grading for more accurate talent matching.
TECHNOLOGIES
Python, Jupyter, NLP, Phantombuster (LinkedIn Scraper), Python, Jupyter Notebook, LinkedIn Scraper
