Auto Identification Process (AIP)

Responsibilities:

• Project Description: Auto Identification Process (AIP) application is develop as analyzing application in order to automate the process of viewing the list of defaulters for the bank i.e. users who have borrowed money from the bank but failed to repay it in their specified duration of time. AIP including various modules such as AIP Admin and Business User Registration, Auto Defaults, Manual Defaults , Re Defaults and Displaying Updated Results
Roles & Responsibilities:
• Installed and configured Hive and also written Hive UDFs.
• Evaluated business requirements and prepared detailed specifications that follow project guidelines required to develop written programs.
• Involved in writing Hive queries to load and process data in Hadoop File System.
• Developed Auto Defaults, Manual Defaults module using MR paradigm.
• Automated shell scripting for server space maintenance

Blog Analysis (Keyword Extraction and Click Stream Processing)
Project Description: Blog Analysis project is based on Data Mining, Big data and ML Concept. System was developed using Hadoop framework, Apache Spark. It use Advanced Machine Learning algorithm to perform clustering and extracting important keyword from source. Blog Analysis helps in enhance the advertising revenue and product citations.

Roles & Responsibilities:

• Preprocessing using Pig Script and NLTK wordnet dictionary
• Evaluated business requirements and prepared detailed specifications that follow project guidelines required to develop written programs.
• Involved in writing Hive queries to load and process data in Hadoop File System.
• Implementation of machine learning algorithms
• Worked on database design using MongoDB.
• Building Mongo-Hadoop Connector using gradlew.