Gursharan Singh Dhanjal

• Perform hands-on data analysis and modeling with huge data sets for the India Data Portal (IDP)
• Discover data sources, import them, clean them up, and make them “portal-ready”
• Statistical modeling, model fitting, machine learning, data mining on large datasets
• Research and work with Data Engineering and Architecture teams to implement new technologies that will facilitate better data integrity, reliability, and enrichment of the portal
• Run regular tests and statistical analysis, draw conclusions on the accuracy of the data
• Dive deep into a wide range of data (agricultural, financial, etc.) to identify opportunities and recommend solutions.
• Assess the effectiveness and accuracy of new data and data gathering techniques.
• Perform ad hoc data mining, exploration, and statistical analyses on complex problem statements
• Write ETL pipelines to make data available for training and testing models both offline and in production.
• Working with Geo spatial and Satellite data and linking to economic indicators

• Driving the vision & strategy for AI & ML at Netsmartz leading a Team of Machine Learning Engineers and Python Full Stack Developers
• Technical architect responsible to architect PoC’s and applications based on:
  • Computer Vision
  • Machine Learning
  • Natural Language Understanding, Processing and Generation
  • Predictive Analysis
  • Recommendation Engines

Responsible for handling GST related data of U.T Chandigarh

My job here was not limited to, but included the following tasks:

• Build Data Pipelines for ETL(Extract, Transform & Load) operations on data received from the central GST portal
• Management of state-wise taxation data received from central GST Network Portal
• Separate pipelines to generate different kind of reports (for each ward in the state) and the required data-sets using complex Oracle SQL queries in conjunction with Python scripts
• Basic predictive analysis base on behavioral / transactional features of taxpayer
• Technologies used: Python, Pandas, Oracle SQL, SQLAlchemy, Scikit-Learn, Matplotlib

(Role: Data Science, Front-end Development)

• Help in database structuring and designing
• Development of complete front-end in AngularJS for the company product/platform
• Managed a team of interns, developers responsible for front-end and back-end development
• Development of Mobile Application for the platform
• This platform is being used for multi-mode data collection in PGIMER and some other healthcare establishments
• Technologies used: AngularJS for frontend, Loopback.io, Nodejs for backend, MySQL database and Ionic for Mobile Application
• Domains worked in: Frontend Development, Hybrid Mobile Application Development, Data Visualization, Data Analysis, Basic Predictions (Machine Learning)

in research project entitled "Haryana Demonstration Project on Wheat Flour Fortification to improve Iron, Folate and Vitamin B12 status in Ambala District" funded by WHO, India and CDC, USA

• Designed and developed web-based application for survey data entry (with error checks & skip patterns) in Python
• Developed data entry manual, trained the data entry personnel and supervised the data entry session
• Optimization of mobile app (Ionic / AngularJS) linked with the web tracking system to record timestamps of sample collection and processing
• Perform dual data entry, check data output, data validations and checks to maintain accurate data on computer systems and in archives and take regular data backups
• Performed cleaning of compiled data sets after completion of data entry, the overall ETL (Extract, Transform, Load) process from two prime data sources, survey data and bio-sample data
• Data analysis (univariate, multivariate) and assisted the statistician in preparing final outcome tables
• Participated in visualizing the analysis outcomes and help to pen down the interpretations and the final report writing & editing process
• This base-line survey proved to be instrumental for Haryana government to implement the Policy of providing Wheat Flour fortified with Iron, Folic Acid, Vitamin B12 through PDS
• Technologies used: Python (Django, Pandas, Numpy, Scikit Learn), R Studio, Javascript (AngularJS/Ionic), Tableau, SPSS
• Domains worked in: Mobile/Cloud based survey development, Data Management, ETL, Data Analysis (Python, R)

• Design and implementation of moderately complex software solutions using multiple platforms (mobile and web).
• Design and manage complex database architectures (MySQL, PostgreSQL).
• Building Data Extraction (Mining) processes, Transformation, Loading (ETL) from multi-dimensional databases / data stores and data exchange pipelines.
• Performed basic data analysis, data visualization, showing insights using Python (matplotlib, plot.ly), Javascript (D3.js)
• Code documentation, configuration management and deep level of debugging
• Fair degree of testing the technical scenarios (manually)
• User, Class, Network & System Architecture modelling as per technical scenarios
• Technologies used: PHP (Codeigniter, Zend), Javascript (AngularJS, Ionic, D3.js), Python (Django, Numpy, Pandas, Matplotlib, Scrapy), Nodejs, GIT, MySQL, PostgreSQL
• Domains worked in: Hybrid Mobile Application Development, Natural Language Processing, Web