• Analyzed requirements and developed comprehensive project plans to guide data science initiatives

• Strategized and implemented detailed work plans to ensure project milestones and deadlines were met

• Designed and developed an innovative academic enhancement product using LangChain and LLM, improving teaching and correcting workflows

• Collaborated effectively within a team using Agile methodologies, resulting in on-time project delivery that met all objectives
• Built and executed high-performance data pipelines to process massive datasets exceeding 10B rows. Employed big data technologies, such as Spark and SQL in Databricks, to source and compile grocery Ad data for forecasting and analysis
• Engineered highly accurate predictive models, predicting ad effectiveness for three distinct product categories across two banners. Attained R2 score of 0.85, enabling compelling storytelling and influencing business decisions
• Streamlined dashboard data retrieval by refining SQL queries, slashing their quantity by over 60%, resulting in a significant reduction in cloud resource consumption and markedly enhancing overall processing speed
• Crafted an interactive dashboard that visually presents diverse customer metrics, unveiling spending patterns across customer types, thereby facilitating in-depth analysis of purchase behavior and empowering strategic marketing/inventory management
• Interacted with various stakeholders to ensure proper utilization of new product, which directly helped their reporting capabilities and accuracies

• Devised a Machine Learning model using Python and OpenCV for image analysis, facilitating automatic table detection and preservation
• Semi-automated solution significantly cut down manual processing of paper-based bills, resulting in a 50% reduction in both time and space requirements
• Developed and deployed predictive models using Python, R, and SQL to optimize room pricing strategies, resulting in a 15% increase in average revenue per room
• Implemented machine learning algorithms such as linear regression, decision trees, random forests, and gradient boosting to forecast demand and optimize inventory management, achieving a 20% reduction in overbooking rates
• Conducted exploratory data analysis (EDA) using Python libraries like Pandas, NumPy, and Matplotlib to identify key trends and patterns in customer booking behavior, leading to targeted marketing campaigns that boosted customer engagement by 25%
• Utilized clustering techniques such as K-means and hierarchical clustering to segment customers based on booking preferences and behaviors, enabling personalized marketing strategies that increased repeat bookings by 18%
• Employed time series analysis using ARIMA, Prophet, and LSTM models to forecast booking trends and seasonal demand, for better resource allocation and staffing decisions
• Leveraged Natural Language Processing (NLP) techniques with libraries such as NLTK and SpaCy to analyze customer reviews and feedback, providing actionable insights that improved service quality and guest experience
• Collaborated with teams including marketing, operations, and IT to translate business requirements into data-driven solutions, ensuring alignment with overall business goals