Data Analyst with a strong focus on data visualization and predictive modelling at Cyient. Proficient in SQL and Power BI, successfully transformed complex datasets into actionable insights, resulting in a cost savings of 3.4K CAD in 2022. Collaborative team player, delivering data-driven solutions that improve decision-making processes.
Project Description
GE is known for providing software and advisory services around operational technology and infrastructure, jet engines, power plants, and locomotives. The purpose of project is Real time condition monitoring of the mining equipment such as Jaw/Impact crusher using robust statistical techniques and predictive failure detection to prevent unplanned downtime.
Responsibilities
· Performed Data Preparation: Cleaning, transformation and understanding the data.
· Performed EDA.
· Performed Text Pre-processing techniques and analysis using NLTK Library
· Performed various Text analysis techniques to get better accuracy.
· Developed predictive model to predict the right label using machine learning algorithm and various optimization techniques.
· Developed ETL jobs from various sources such as Oracle Database, MySQL Database, Flat Files (Excel and Google Sheet) and loaded into target databases using Talend Open Studio.
· Interact with business community and gathered requirements based on changing needs. Incorporated identified factors into Talend jobs to build the Data Mart.
· Tuning the SQL source queries to restrict unwanted data in ETL process.
· Building Visualizations, reports and interactive dashboards on OLAP Database built as per customer needs.
· Developed Power BI model (Star & Galaxy Schema) to build reports based on customer requirements.
. Modelled Data in Power BI using SQL for performance tuning of reports.
· Built interactive visualizations and configured relative filters, slicers, bookmarks and drill-through from summary to detailed reports.
Environment:Python, Jupyter notebook/Spyder, Linux, Power BI, Windows 7