Data Scientist - AI/ML Engineer
SlashNext
Total years of experience :4 years, 11 Months
• Led a team to develop a malicious and benign SMS text classification model using Deep Learning BERT Algorithm, achieving 97% accuracy and reducing scams by 37% in the USA, saving $60 million annually.
• Led NLP research initiatives to advance text analytics capabilities, exemplified by the development of a BERT model achieving 97% accuracy in sentiment analysis.
• Led the design and implementation of ML algorithms for anomaly detection, including an Random Forest model with 85% accuracy in detecting network security breaches.
• Collaborate with data engineering for scalable, real-time monitoring, ensuring system reliability.
• Drive cross-functional collaboration to identify business challenges and develop ML/AI solutions. Lead the development of a Random Forest classifier achieving 96% accuracy in customer churn prediction, facilitating proactive retention strategies and reducing attrition by
25% within six months.
• Developed a collaborative filtering recommendation engine utilizing models like Matrix Factorization and Collaborative Filtering, achieving a revenue increase of $10 million.
• Leveraged machine learning techniques such as Association Rule Mining to extract actionable insights from large datasets, resulting in a 30% boost in cross-selling opportunities.
• Extracted sales data from AWS Redshift using Python, applying cleaning and feature engineering techniques with Pandas and NumPy, enhancing data quality and enabling more accurate predictions with models like Random Forests and Gradient Boosting Machines (GBMs).
• Optimized data storage systems, implementing techniques such as data compression and indexing, reducing access times by 40%.
• Calculated KPIs and established a tracking pipeline to assess the impact of the recommendation engine on KPIs.
• Collaborated with international clients such as Singtel, and Comfortdelgro, delivering tailored solutions that boosted efficiency by 15%
• Actively participating in daily scrum meetings to ensure timely project completion and reduce project turnaround time by 10%.
• Utilized Python libraries like easyocr, numpy, pandas, matplotlib, and scikit-learn, contributing to a 25% reduction in data processing time.
• Trained and validated ML models, leading to a 30% improvement in model accuracy, and deployed them using advanced techniques, which decreased deployment time by 20%.
• Demonstrated proficiency in building deep learning models for a face detection attendance system, achieving an exceptional accuracy rate of 97%, ensuring reliable and efficient attendance tracking.
• Led the design and implementation of machine learning algorithms customized for restaurant review analysis, resulting in sentiment analysis accuracy of 90%, thereby enhancing decision-making processes within the food service industry.
Major Courses: Data Science, Machine Learning, Deep Learning, Natural Language Processing, Computer Vision, Research Methods, Thesis
Major Courses: Data Structures and Algorithm, Programming and OOP, Statistics and Probability, Calculus and Linear Algebra, Data Mining and Data Warehousing, Data Science and Machine Learning