•Designed and developed ETL processes to support data warehousing and reporting requirements by automating data integration from multiple sources (relational and non-relational databases).•Power BI and grafana reports were created to remotely monitor and analyze data collected from different factories.•Used statistical methods and developed Machine Learning/Deep Learning models to detect anomalies such asloss of performance, reduction in flow rate in industrial machines (Numeric, categorical, time series data).•In all data analytics studies, end-to-end, needs are identified, algorithm is designed, data is received from relational and non-relational data source. Data is prepared, analyzed, visualized, modeled, tested and deployed•Gitlab was used for version control. Docker was used to lead to a stable development environment and reducesystem downtime.•Meetings were organized with the teams to discuss needs, project progress, expectations, information about theprocess, etc.•Worked on international projects and Tubitak projects. Presentations were made, documents were written.•LLMs applications were developed using open source models.

- Data analysis was performed with Pyspark- Future sales/stock forecasting and seasonality analysis were performed on Time Series data- Presentations on Pyspark and SQL window functions were made to the Analytics team- An association analysis was conducted and recommendations were prepared based on this analysis and presented to the analytical team

We established a company in high school with 5 friends for the competition. We determined products, made sales between high schools and tried to realize our projects