Working on Hadoop Cluster with current size of 56 Nodes and 896 Terabytes. Writing Map Reduce Jobs, HIVEQL, Pig, Spark. Exporting and Importing data into HDFS, HBase and Hive using Sqoop. Loading data into Hive partitioned tables. Involved in creating Hive tables, loading with data and writing Hive queries. Created reports for the BI team using Sqoop to export data into HDFS and Hive. Work closely with the business and analytics team in gathering the system requirements. Also, performed the feasibility analysis, work estimations and other related documentations for the project.

Created a Machine Learning model of Ticket classification based on the ticket description, level and priority. In order to achieve that I tried different algorithms and implemented the most convenient one based upon their accuracy. After the upper management approvals and demo of this project it was successfully deployed and got a star award for the same. Implemented another Machine Learning model on Mail sentiment analysis using Natural Language Processing. By using this model user was able to predict the sentiment of the Client mails.

Ticket creation based on the description and mail sentiment analysis

Worked on various tools and technologies of hadoop