AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Building Scalable Data Analytics Products & Solutions at Capital One
I build scalable data & analytics products that transform complex, high-volume data into decision-driving platforms and business solutions. With 7+ years of experience across data analytics, platform engineering, and enterprise data transformation, I have spent the past 4.5+ years at Capital One working on large-scale data platforms, analytics engineering, and enterprise data initiatives. My work has focused on designing production grade pipelines, scalable analytical frameworks and reusable data products used by Data Science, Risk, Marketing and Strategy teams across organisation. My experience sits at the intersection of data, analytics, platform engineering and product thinking. I enjoy partnering cross-functionally to translate business problems into scalable technical and analytical solutions with measurable operational impact. My work has included: • Building distributed Spark/SQL-based data pipelines processing large-scale enterprise datasets • Developing production ETL orchestration frameworks using Airflow • Designing model-ready analytical datasets and reusable data products for downstream modeling and analytics workflows • Leading large-scale enterprise data integration and standardization efforts, including post-merger Discover portfolio integration initiatives • Driving platform scalability, data quality, validation, and operational efficiency across business-critical workflows • Spearheading reusable analytics and data product initiatives that improved onboarding efficiency and operational throughput across enterprise programs • Partnering with business, strategy, and cross-functional stakeholders to define analytical requirements, prioritize scalable solutions, and support data-driven decision-making I’m particularly interested in scalable data systems, analytics infrastructure, product strategy, data product development, and buildin
Illinois Institute of Technology
Master’s Degree, Computer Science
January 1, 2016 – January 1, 2018
SRM IST Chennai
Bachelor’s Degree, Computer Science
January 1, 2012 – January 1, 2016
Capital One
Principal Data Analyst- Credit Finance Risk Model
August 1, 2024 – Present
Capital One
Senior Data Analyst- CreditWise & Card Messaging/Marketing Transformation
January 1, 2022 – August 1, 2024
Wintrust Financial Corporation
Data Analyst- Lending & Investment Analytics
January 1, 2020 – February 1, 2022
Great Lakes Advisors
Data Analyst, Investment Operations
September 1, 2018 – January 1, 2020
Greater Chicago Area
Illinois Institute of Technology
Student Employment Ambassador
January 1, 2018 – January 1, 2020
Greater Chicago Area
Illinois Institute of Technology
Research Assistant (Machine Learning)
November 1, 2017 – August 1, 2018
Greater Chicago Area
HireSphere, Inc.
Machine learning intern
August 1, 2017 – December 1, 2017
Chicago, Illinois
Computer Discover Camp at Illinois Institute of Technology
Lego Mindstorm and soft circuits instructor
June 1, 2017 – July 1, 2017
Greater Chicago Area
IBIZ Consulting Services
Summer Internship
May 1, 2014 – June 1, 2014
Chennai Area, India
Predicting Prospective Customer Conversions For Senior Life
April 1, 2018 – Present
This project was a part of hackathon organized by Depaul and Chicago ML community. Senior Lifestyle is a senior housing Management Company that operations over 180 senior housing rental communities across 28 states.The prospect is connected with the community and a series of activities between the community sales team and prospect take place in an effort to turn the prospect into a permanent resident of the community and in how many days, thus binning them as Hot (move in within 30 days), Warm (move in within 90 days), and Cold (just browsing – no set move-in date) to classify prospects and determine which sales activities are necessary.
Content Based Image Retrieval Search System
October 1, 2017 – December 1, 2017
This project is about content-based image retrieval(CBIR) by extracting features like color and texture. - Responsible for performing retrieval experiments were performed by developing a database of images and querying the image to retrieve the set of similar images. - Responsible for implementation of Color Feature which involved conversion to HSV color space and maps pixel intensities into an HSV cylinder using color histograms. -Deciding the tradeoff between bins sizes of the histograms. - Defined a Global feature for each image in the database. - Defined a local color feature for each image in the database by dividing the image into segments and defining a global feature for each segment closely related to human visual perception. -Responsible for implementation of Texture Feature refers to visual patterns of an image. - Defined Co-occurrence matrix for each image in all directions. - Parameters taken into account were moment of inertia, Angular Second Moment, Correlation and Homogeneity. - Results showed that when both features are taken into account showed better results(precision = 2 ) independently both feature (precision = 5)
Computer-Vision-Projects
August 1, 2017 – December 1, 2017
-Responsible for various implementation and usage of various openCV functions and python functions using python 3.6. Some of the implementations and usage discussed are computer vision and image processing problems including capturing standard images, live images, modifications and implementations of various OpenCV functions. - Responsible for implementation of Harris corner detection, localization for an image, and also for two images(one be with the different viewpoint) feature detection and matching. - Responsible for implementation of non-coplanar camera calibration which also includes implementation of camera calibration for a noisy image with robust estimation to remove outliers using RANSAC. - Responsible for implementation of Epipolar lines on the two stereo images by inputting the point interactively capable to be performed on both the images.
Learning With Rationals For Text Classification-Amazon product reviews
August 1, 2017 – November 1, 2017
The main aim of the project is to analyze people's sentiments, attitudes, or emotions towards a particular product they bought from Amazon.com and posted their views in the form of comments/reviews on the website. Detailed Report: https://github.com/dummyGetUsernames/cs595-01/blob/master/report.pdf -Designed a Human Simulator, for providing labels to the reviews using the whole training dataset, which will later be helpful in updating the weight for each feature. -Analysed the two methods of traditional method and learning with the rationals method and made comparisons. -Experimented both the methods and the results were showing learning with rationals work better than traditional method for NAiive Bayes and Logistic regression L2 regularization
Predicting Policing-using Machine Learning to Detect High Crime Areas
February 1, 2017 – April 1, 2017
Goal: The following project is about the crime-detection about a locality based on the demographic and economic information provided in the dataset. Dataset: We are provided with data for the per-capita rates around the country out task was to build a model to predict crime rate. -Responsible for calculating the per capita violent crimes variable by using population and the sum of crime variables considered violent crimes in the United States: murder, rape, robbery, and assault. - Responsible for dealing with missing values for rape, because apparently there was some controversy in some states concerning the counting of rapes, which resulted in incorrect values for per capita violent crime. - Responsible for calculating and predicting the areas in the US with the highest percentage of crimes and the communities involved.
Automated Essay Scoring
January 1, 2017 – April 1, 2017
Goal: This project aims at to build a generalized automated grading of student-written essays, which concerns on implementing a model to help schools teachers to accelerate grading process and improve the analysis of student’s analytical and writing skills for both short and long answers - Feature Extraction from raw data of essays using Python and R. - Classify extracted features using classification algorithms like random forest, Support Vector Machines, Neural networks, and logistic regression using sci-kit - Eventually, we got good accuracy on short answers and in the case of long answers binning them into ‘good’ and ’bad’ instead of final scores gave better scores. - Used data visualization software like Mircosoft Excel and Weka for accuracy. - Organized and managed tasks for smooth project completion
SIMULATED ANNEALING BASED OPTIMIZATION FOR VIRAL MARKETING
January 1, 2016 – Present
This study aims at creating an efficient and enhanced model to maximize the utility of viral marketing in social networks. Our project facilitates locating the target users who are interested in purchasing a product. It is also claimed in this work the idea used can be readily adopted by existing networking sites thereby increasing their efficacy in product marketing. Presented paper in International Journal of Emerging Technology in Computer Science and Electronics[IJETCSE 2016 April edition VOLUME 21/Issue 4]
WiFi INDOOR POSITIONING
March 1, 2013 – October 1, 2013
This project was aimed to be used in large places such as big offices and shopping malls for easy and convenient navigation for a new user. It enables an indoor positioning system for a user inside a building using smartphones Wi-Fi signals and mapping his own positon without surpassing the security access.
Neural Networks and Deep Learning
Coursera
June 24, 2026 – Present
IOS APPLICATION DEVELOPMENT
SRM University
June 24, 2026 – Present
Advances in Positioning, Navigation and Communication APNC 2014
SRM University
June 24, 2026 – Present
Cultural Fit Analysis
The candidate's project history shows a strong inclination towards data science, machine learning, and analytical problem-solving, which aligns well with a data-driven culture. Their experience in financial services indicates an understanding of regulatory environments and risk mitigation. The diversity of projects, from viral marketing optimization to predicting Alzheimer's, demonstrates intellectual curiosity and adaptability. However, the projects are predominantly academic/personal, and the specific technologies used in professional roles are not explicitly detailed, making it harder to assess direct cultural alignment with a highly specific tech stack.
Soft Skills & Operational Fit
The candidate's experience at Capital One and Wintrust Financial Corporation suggests an ability to operate in structured corporate environments, manage projects, and mentor junior analysts. The project descriptions indicate a methodical approach to problem-solving and an understanding of business impact. Collaboration with diverse teams (Legal, Risk, Operations, Product, Technology) highlights strong interpersonal and operational fit.