Manasi Rawas

– Engineered and optimized machine learning models (Logistic Regression, Random Forest, XGBoost) using Scikit-learn, improving predictive accuracy and model robustness through advanced feature engineering – Designed end-to-end data pipelines including data cleaning, preprocessing, and transformation using Python (Pandas, NumPy), reducing model training time by ~20-25% – Performed exploratory data analysis (EDA) on structured datasets (100K-500K+ rows), identifying key patterns and business insights to guide modeling decisions – Delivered forecasting and predictive insights to support data-driven decision-making, improving planning efficiency and operational outcomes – Collaborated with cross-functional stakeholders to translate business problems into scalable ML solutions aligned with real-world use cases

– Developed predictive Machine Learning models and enhanced accuracy through advanced feature engineering. – Automated data cleaning and preprocessing workflows using Python, Pandas, and Scikit-learn. – Conducted data visualization and pattern analysis with Matplotlib and Seaborn for real datasets.

– Automated reporting processes using Excel VBA, saving over 10 hours per week and reducing manual effort by 30%. – Analysed large datasets with Python, SQL, and Pandas to identify trends and anomalies, enhancing efficiency by 15%. – Developed interactive dashboards in Tableau, Power BI, and Google Data Studio, which cut decision-making time by 20%.

– Collected and translated business requirements into clear documentation, reducing rework by 20%. – Drove process improvements, cutting reporting turnaround by 25% and enhancing decision-making speed. – Led UAT and end-user training, resolving 90% of issues pre-release and boosting adoption rates by 30%. – Managed supply chain and CRM initiatives, reducing inventory by 15% and improving customer satisfaction by 12%.