• Orchestrated the migration of 120,783 data points to a cloud environment, achieving enhanced scalability and performance.
• Implemented A/B testing methodologies to assess cloud architecture configurations, resulting in optimized infrastructure and cost efficiency.

Tools: Google Cloud Platform (GCP), BigQuery, Google Cloud Storage (GCS), Cloud SQL, Airflow, Oracle, Data Definition Language (DDL).

• Identified factors contributing to patient no-shows in medical appointments, enabling healthcare providers to improve patient care and resource utilization.
• Presented actionable insights derived from A/B testing and statistical analysis, driving operational efficiency and cost savings for healthcare organizations.

• Extracted customer satisfaction survey data from the company's database using SQL queries, focused on relevant metrics such as product/service ratings, feedback comments, and demographic information.
• Cleaned and preprocessed the extracted data using SPSS to ensure data quality and consistency, handling missing values and outliers as necessary.
• Utilized SPSS for statistical analysis to uncover patterns and relationships within the customer satisfaction data.
• Generated descriptive statistics and visualizations, to illustrate key insights and trends in customer satisfaction levels.
• Created interactive dashboards and reports using data visualization tool Power BI, to present findings clearly and intuitively for stakeholders.
• Collaborate with cross-functional teams to develop strategies and initiatives based on the insights gained from the analysis, such as product/service improvements, customer engagement initiatives, and targeted marketing campaigns.

Successfully developed a student performance prediction system that provides actionable insights to educators and administrators, enabling them to identify at-risk students early and implement targeted interventions to support their academic success.

• Clean and preprocess large datasets containing student information using SQL and Python libraries like Pandas to ensure data quality and consistency.
• Utilize machine learning techniques, including regression and clustering, to build predictive models that can identify patterns and trends in student performance data.
• Implement A/B testing methodologies to assess the effectiveness of different model configurations and fine-tune algorithms for optimal performance.
• Create detailed reports and interactive dashboards using Tableau to visualize key metrics and performance indicators for stakeholders.
• Collaborate closely with product and engineering teams to integrate the predictive model into educational platforms and recommend actionable insights to improve student outcomes.

• Collaborate with the salesforce and marketing teams to gather comprehensive student interaction data, including demographic information, learning preferences, and past engagement metrics.
• Utilize SQL queries to extract relevant data from Salesforce databases and preprocess the data using Python libraries like Pandas to prepare it for analysis.
• Analyze the collected data to identify patterns and trends in student behavior, gaining insights into their learning preferences and needs.
• Develop collaborative machine learning algorithms using Python, focusing on techniques especially collaborative filtering and content-based filtering, to recommend personalized learning paths based on individual student profiles.
• Collaborate with stakeholders and conduct direct meetings to understand their requirements and gather feedback on the initial prototype of the recommendation system.
• Optimize the recommendation system based on feedback from stakeholders and ongoing monitoring of key performance indicators, such as recommendation accuracy and user satisfaction.