Data Scientist

Adika Jain

+*(***)***–**** - *******@****.***.*** - linkedin.com/in/adika-jain/

Summary

Software Engineer with around 4 years of professional experience in data warehousing, analytics, cleaning, extraction, and visualization. Focused on optimization, algorithm design, machine learning, big data, and statistical analysis. I like to apply these focus areas into solving specific problem in any given domain. As a graduate student, I am learning how a balanced approach comprising of Computer Science, Mathematics and Statistics courses can be applied in extracting meaningful insights from the complex and large nexus of any category data all around us. Education

Illinois Institute of Technology, Chicago, USA. Aug 2019 – May 2021 Master of Science – Data Science GPA: 3.71/4.00

Related Courses: Machine Learning, Applied Statistics, Big Data Technologies, Data Preparation and Analysis, Public Engagement for Scientists, Statistical Learning, Deep Learning, Probability and Statistics, Statistical Learning, Special Problems, Data Mining.

Walchand Institute of Technology, Solapur, INDIA. Aug 2019 – May 2021 Bachelor of Engineering – Computer Science GPA: 3.51/4.00 Related Courses: Operating Systems, OOP Methodology, Data Structures, Computer Networks, Database Management Systems, Design and Analysis of Algorithms.

Technical Skills

Languages: Python, sC++, UNIX Shell Scripting, Data Structures, R Databases and Cloud: MySQL, PostgreSQL, Oracle

Frameworks and APIs: Anaconda, NumPy, SciPy, Scikit-Learn, Matplotlib, TensorFlow SDLC and Version Control: Agile, Waterfall, Iterative, Git (GitHub) Machine Learning & Statistics: Linear Regression, Multiple Regression, KNN, Neural Networks, CNN, Logistic Regression, Decision Tree, Random Forest, A/B Testing, ANOVA, Hypothesis Testing, NLP. IDEs and Tools: Jupyter, Spyder, R Studio, Hadoop, AWS, Kibana, Tableau, Map-Reduce, Spark SQL, Hive Work Experience

AArete, Chicago, USA. May 2020 – July 2020

Sept 2020 – Dec 2020

Data Analytics Intern (Python, R, Machine Learning, Kibana, MySQL)

Build a Kibana analytical dashboard to have easy identification of spikes/outliers in healthcare claims. Analyzed month- over-month variations in percentages the plans will pay for a covered health care service (CPT) and derived insights by segregating them into buckets 5%, 10% and 20%.

Recreated a suitable data set of members/patients consisting of their claims, economic, and co-morbid conditions to predict their likelihood of suffering from Type-2 Diabetes in future. Employed various classification algorithms like random forest, decision tree and logistic regression to compare their performances and understand which algorithm best fits the use case. Random Forest performed best with 87% accuracy rate.

Wrote SQL queries for verifying if the payments to providers are aligned with respective contract matrices of a payer and to identify any overpayments that happened along any of the Medicaid, Medicare, and Commercial lines of business for potential saving opportunities.

Resolving payment intelligence healthcare claims requests for finding cost-saving opportunities in areas like PTP, MUE, 1-day rule healthcare policies by writing complex queries and functions in SQL database.

Implemented Python scripts to parse large XML log files of users statistics having different formats to a single pandas data frame, processed and prepared the data using Pandas libraries to make the data compatible for generating reports/dashboards in Kibana.

Auditing different transportation client’s data to uncover duplicate vendors invoices by aligning disparate datasets, fuzzy string matching using FuzzyWuzzy package of Python on fields like name, address to help clients reduce the risk of fraud.

Persistent Systems Limited, Pune, INDIA. Oct 2015 – Jun 2019 Senior Software Engineer (C, C++, Data Structures, PostgreSQL, Machine Learning, Python, R, Shell Scripting)

Performed product enhancements, resolution of QA and customer filed defects for IBM Netezza PureData Analytics, a data warehousing application that designs and ships high performance data warehouse and advanced analytics.

Exposed various loopholes in the code of the product with extensive debugging and proposed optimized solutions for the same in various components of database like query parser, compiler, optimizer, workload management, encoding along with others on LINUX environment.

Improved the serviceability and performance of IBM Netezza by boosting the execution time of a time-consuming process to 170-190% using a framework implemented in Python & Machine Learning thereby reducing the overall start time by 50-65%.

Using R language, resolved customer issues related to analytics functions of IBM Netezza Analytics product. Got a substantiate amount of hands-on on various analytics functions, data sets, data frames and machine learning algorithms.

Owned the security module unit of IBM Netezza, where I managed the receipt, investigation, and resolution of security vulnerabilities in libraries such as Binutils, Botan, PostgreSQL and Java.

Coordinated with off-shore business and emergency team to resolve time-critical escalations for 80+ clients such as Neilson, Fidelity, Citicorp, Bank of America, and Fannie Mae.

Ported and compiled open source packages like Hadoop, JBOSS (EAP), Perl, Python, MySQL, Tensor Flow, Spark etc. using (make, cmake, maven, and ant tools), packaging in Debian & RPM format open on IBM Power UNIX Systems to create an open ecosystem, using the POWER Architecture to share expertise, investment, and server-class intellectual property to serve the evolving needs of customers and industry. Projects

Platform for Building Business to Business Application Spring, Hibernate, RESTFUL Services and MySQL (May’15)

- Implemented automation of business processes aimed at communication required within the producers, manufacturers and retailer chain. The project supported multiple trading models for various platforms on the internet for and by commercial organizations mainly supporting Order Management. Machine Learning Machine Learning & Python (Aug’19)

- Predicted the loan status of historical dataset from previous loan applications by cleaning the data, applying different machine learning algorithms like KNN, Decision Tree, SVM and Logistic Regression on the data. Best accuracy of the model was predicted with Logistic Regression.

Airbnb Data Analytics Project PySpark, MLlib, SparkSQL & Python (Nov’19)

- Developed a data processing pipeline using Big Data technologies to insert, modify, transform and implement Big Data techniques to research relation between proposed data and derived meaningful understanding of data streaming on Airbnb data from Kaggle.

Image Analytics Project Convolutional Neural Networks, Tensor Flow, Python and Deep Learning (Nov’19)

- Implemented a CNN model on an image data sets of 10,000 skin lesions on which machine learning and image classification would be applied to identify the category of Cancer. Single Shot Detector Convolutional Neural Networks, Tensor Flow, VGG16 and Pytorch (April’20)

- Implemented an object detection system in computer vision that aims to find and classify objects in images using bounding boxes using feed forward neural networks and VGG16 architecture. Certifications

R Programming by Johns Hopkins University, Coursera October 2019

Machine Learning with Python, Coursera August 2019

Python for Data Science and AI, Coursera June 2019

Data Science Methodology, Coursera May 2019

Open Source tools for Data Science, Coursera May 2019

What is Data Science, Coursera May 2019

Machine Learning by Stanford University, Coursera March 2018 Awards

Honored with ‘High Five Award’ four times during my work tenure in Persistent Systems in recognition of my efforts, dedication and diligence put into to resolve critical challenges ultimately benefitting the business productivity. Volunteering Experience

Network Chair of the Machine Learning Club at Illinois Tech.

Volunteer and member of ACMW Club at Illinois Tech.

Contact this candidate