Praveen Jain
Verified Data Scientist
Data Scientist
Praveen Jain is a Data Scientist with over 9 years of experience, including 8 years in analytics, predictive modeling, demand forecasting, and machine learning. Currently serving as Chief Engineer (Machine Learning) at Samsung R&D, Praveen excels in solving complex business problems through data-driven insights and innovative solutions. He has a proven track record of improving model accuracy and optimizing business processes across various industries.
PREVIOUSLY AT
Samsung
LOCATION
Bangalore, India
AVAILABILITY
Full-time
Skills
ANN
Boosting
CNN
Data Science
Decision Tree
Linear Regression
LSTM
Market Basket Analysis
MySQL
PySpark
Python
R
Random Forest
RNN
SAS
+3 More
Work Experience
Chief Engineer (Machine Learning)
Samsung R&D
2022 - 2024
- Developed a Customer Experience Journey (CEJ) dashboard for Samsung.com to enhance user engagement and analytics.
- Working on a Real-Time Artwork Recommendation System using PENUP Artworks to personalize user experience.
- Developing a model to accurately tag user-created artwork on the Samsung Artwork App (PENUP).
TECHNOLOGIES
SAS, R, SQL, Tableau, PySpark, Python, Linear Regression, Logistic Regression, Decision Tree, Random Forest, Boosting, Support Vector Machine, K-Nearest Neighbor, Market Basket Analysis, Naïve Bayes, K-Means Clustering, K-Medoids (PAM), K- Modes clustering, K-Prototype clustering, ANN, RNN, LSTM, Transformers
Data Scientist
Antuit.ai
2020 - 2022
- Demand Forecasting: Created an ML model to forecast product shipping quantities for a global logistics provider, improving forecast accuracy by 5% over traditional methods.
- Anomaly Detection: Developed an Anomaly Detection model for a cosmetics company, enhancing demand forecast accuracy by 3%.
- Sell-in Forecast: Built a forecasting ML model for sell-in quantities using a conversational approach for a multinational consumer goods company.
TECHNOLOGIES
SAS, R, SQL, Tableau, PySpark, Python, Linear Regression, Logistic Regression, Decision Tree, Random Forest, Boosting, Support Vector Machine, K-Nearest Neighbor, Market Basket Analysis, Naïve Bayes, K-Means Clustering, K-Medoids (PAM), K- Modes clustering, K-Prototype clustering
Data Scientist
Arvind Fashions Limited
2019-2020
- Customer Centric Store Assortment Optimization: Implemented ML models to optimize store assortment and demand patterns, resulting in a 4-5% sales growth and a 5% uplift in Return on Sales (ROS).
- Markdown Optimization: Developed a dynamic discounting model for slow-moving products, using predictive and optimization techniques to increase sales by 3%.
TECHNOLOGIES
SAS, R, SQL, Tableau, PySpark, Python, Linear Regression, Logistic Regression, Decision Tree, Random Forest, Boosting, Support Vector Machine, K-Nearest Neighbor, Market Basket Analysis, Naïve Bayes, K-Means Clustering, K-Medoids (PAM), K- Modes clustering, K-Prototype clustering
