SUMMARY
Accomplished software engineer with 2.11 years of experience in developing data lineage, code automation, metadata, and data mapping components that enable meaningful insights and support strategic decision-making. Highly dedicated enthusiast proficient and certified in Python, Java programming, statistical, and analytical skills aspiring to leverage advanced techniques of data science, machine learning, and artificial intelligence for a better ecosystem
KEYSKILLS
Languages: Python, MySQL (Data Definition, Data Manipulation, Data Control, Transaction Control, and Data Query Commands, Joins, Views, Aggregate Functions, Window Functions), Pandas, NumPy, Scikit-Learn, Matplotlib, Seaborn, Java, JSP, Servlets, XML, JavaScript, HTML, CSS
Skills: Mathematics, Quantitative Analytics, Data Science, Perform Data Extraction, Data Cleansing & Transformation, Data Analysis, Data Visualization, Statistics, Relational Databases, Machine Learning Techniques, Predictive Modeling, Classification Techniques, Technique Validation, SQL Programming, Feature Engineering, Hypothesis Generation, NLP, Java Programming, Product Development, Debugging, Software Development, Performance Improvements, Code Quality, Code Reviews, Applications Support, Interpersonal and communication skills, Adaptability, Logical Thinking
Tools: Jupyter Notebook, Google Colab, PyCharm, NetBeans, Microsoft SQL Server Management Studio, Oracle SQL Developer, Git, Eclipse
Machine Learning: Supervised Learning Regression Techniques - Linear Regression, Gradient Descent, Supervised Learning Classification Techniques - Logistic Regression, Bagging, Boosting, and Ensemble models, Unsupervised Learning Techniques - K means Clustering, KNN, and Principle Component Analysis
Operating systems: Windows and Linux
ACADEMIC PROJECTS 1) Credit risk analysis using supervised machine learning algorithms Objective:
Credit risk refers to the threat associated with a borrower's capacity to repay a bank’s loan as well as the interest rate charged. The project's primary goal is to predict credit defaulters as loan providers find it difficult to give loans due to inconsistencies in credit histories. As a result, the majority of clients accept the risk of default, and loan providers struggle to find the proper customer. Outcome: The project's optimal accuracy in prediction helps lenders mitigate risks, maximize profits by giving credit to just those borrowers who are most likely to repay their debts while reducing losses by not providing loans to defaulters. Key skills: Data collection, Data pre-processing, Model building, Model evaluation
2) Data mining using an unsupervised clustering algorithm Objective: Given a non-linear clustering dataset, the main objective is to utilize conscience online learning mechanism (kernel k-means) over kmeans as the base algorithm to form homogeneous and heterogeneous groups such that objects in the same group are more similar to each other than to those in other groups.
Outcome: Data clustering plays an indispensable role in various fields such as computer science, medical science, computational biology, mobile communication, and economics. The project’s outcome is extremely useful in anomaly detection, digital image clustering, video segmentation, and color image segmentation.
Key skills: Data collection, Algorithm design, Clustering analysis, Cluster validation
PROFESSIONAL EXPERIENCE
Software Dev Engineer Erwin-Quest | Hyderabad, India
Backend Development Database Front-End Development Product Support Feb '19 - Present Demonstrated work history of developing metadata-based product specifications for code automation, data lineage, and data mapping to derive business insights from data management Performed successful migration of struts codebase to the latest model–view–controller framework using Java 8, relational databases (MS SQL Server, Oracle), and version control technologies Boosted robustness of the web application by fixing hundreds of security-related vulnerabilities
Constructed & debugged 20+ SQL queries for business logic to interact with the database Attained 25% improvement in application's performance with minimal query execution time by using JDBC batch processing
Front-End Development
Designed user-Interface components that require 50+ input data validations for user interaction Administered a balance between functional and aesthetic design and improved user engagement by 80%
Product Support
Exercised team activities and presentations that enabled over 5+ clients with the application knowledge
Hackathons/Other relevant achievements
Python and SQL certified from HackerRank, India | October 2021 Full Stack Development – Java certification from TalentSprint, Hyderabad, India | July 2018 - November 2019
