About Chiranjeev
As a Primary Data Analyst with the Office of Academic Career Development (OACD) at the University of Pittsburgh, I focus on enhancing postdoctoral outcomes by analyzing key factors influencing career trajectories. My contributions to a landmark study of 268 postdoctoral researchers involved advanced statistical analyses and development of regression models, significantly improving support strategies for transitioning faculty members.
My career is driven by a passion for data analytics and machine learning, fields where I apply rigorous statistical modeling and machine learning algorithms to transform raw data into actionable insights. My analytical acumen, underscored by a lifelong fascination with mathematics and science, empowers me to tackle complex real-world problems effectively.
My passion for data analytics and machine learning is deeply rooted in its power to solve real-world business challenges. Throughout my academic and professional journey, I have been consistently driven by the opportunities to leverage my analytical skills to enhance decision-making processes in business environments. The integration of mathematics and science within the fields of data science and analytics has not only captivated me but has also been the backbone of my approach to analyzing data. My expertise in statistical modeling, machine learning algorithms, and data visualization has proven invaluable in transforming complex business data into strategic insights that drive efficiency and innovation.
The percentage symbol (%) represents the level of expertise, exposure, and projects worked on.
Programming Skills
-
Python
90% -
SQL
80% -
Data Structures
60% -
Java
30%
Frameworks
-
Pandas
70% -
Scikit-Learn
70% -
NumPy
60% -
NLTK
60% -
OpenCV
40%
Tools
Pandas
Power BI
Tableau
AWS
SQL
Jupyter
Google Cloud
MongoDB
Apache Spark
MongoDB
GitHub
VS Code
Soft Skills
-
Hindi
100% -
English
90%
Resume
Working History
-
Data Analyst
Jan 2023 - Present
• Applied statistical modeling and machine learning techniques for a research project involving 268 post-doctoral researchers to determine key factors impacting researchers success in transitioning to faculty tenure positions. Conducted descriptive and in-depth analysis on 1 million-row dataset to identify data trends and patterns, improve data quality and decision making for imputation on missing data which helped the R&D team make data-focused decision.
-
Data Analyst Intern
May 2023 - Aug 2023
•Extracted data from various multi-platform data sources, conducted interviews, and developed surveys, collaborated with analytics and business intelligence teams to design analysis plan and documentation; contributed to data hygiene and ensure database is well organized, anonymized and easily accessible.
-
Business Data Analyst
Jul 2021 - April 2022
•Enhanced Reporting Efficiency: Transformed data schemas into interpretable & accessible reporting data models with PowerBI, resulting in a reduction in security incidents and cost savings of $30,000.
•Data Engineering and Scalability: Developed and deployed scalable data pipelines using Python and SQL, ensuring data compliance.
•Designed visually appealing dashboards with Tableau and PowerBI, resulting in improved identification of vulnerabilities in the company's IT systems and better compliance with security regulations.
-
Data Science Intern
Feb 2021 - May 2021
• Implemented real-time data monitoring for an 8 million-record customer dataset, enhancing data accuracy and security. This initiative led to a 10% reduction in loan default rates, improving portfolio performance.
•Built predictive machine learning models for loan eligibility, automating the approval process, and increasing loan approval accuracy by 15%, thereby significantly enhancing access to financial resources for small businesses.
•Optimized skin cancer diagnosis for a client by developing a machine-learning model for image classification that achieves a 98% precision rate in identifying various skin lesions.
-
Research Assistant (MIPS Processors)
Apr 2021 - Mar 2021
• Worked as a Research Assistant under the supervision of Dr. Anirban Sengupta, Ph.D., in the domain of Computer Processor Design and Security.
• Carried out research, and developed techniques to quantifiably measure the effectiveness and vulnerabilities of hardware security approaches.
-
Trainee - Geospatial Technology Project (Indian Space Research Organisation)
Aug 2020 - Nov 2020
• Completed an intensive 84-hour training program on "Basics of Remote Sensing, Geographical Information System, and Global Navigation Satellite System" conducted by the prestigious Indian Institute of Remote Sensing.
• Applied acquired skills in Remote Sensing, GIS, and Geocomputation with a strong emphasis on data analytics, showcasing the ability to translate theoretical knowledge into hands-on solutions for real-world challenges.
Education History
Extra-Curricular
Organiser & Tech. Head - Aarambh SKITM 2019
Organised technical fest Aarambh 2019 with participation from all over the city.
Soccer Captain @ Soccer Tournament SKITM 2019
Organized a soccer tournament as a captain, with teams participating from several universities and colleges in Indore - 2019.
Portfolio
Researchers Success Impact Analysis
Dec 2023 – Jan 2024
Data Analysis
Applied advanced Statistical and Predictive Modeling techniques to analyze a dataset involving health science post-doctoral researchers at PITT.Uncovered success patterns among University of Pittsburgh postdoctoral researchers using statistical and machine learning techniques. Analyzing a rich dataset, this project identifies influential factors, enhancing future support strategies.
Detecting Fraudulent Transactions using AI via GANs
Oct 2023 – Dec 2023
Artificial Intelligence
Developed a predictive model capable of identifying fraudulent transactions using real financial data. Employed various visualization techniques. These visualizations which help us gain insights into the characteristics and distribution of fraudulent transactions, enabling us to make informed decisions during the model development process.
Security Analysis Tool: IPDR Processing and SQL Storage
Oct 2023 – Dec 2023
Big Data Analytics
Python tool designed to process IPDR (Internet Protocol Detail Record) data. Intereactive and easy interface allows users to search using a CSV file containing IPDR records. Bulk Search (ZIP): Enables users to perform bulk searches by providing a ZIP archive containing multiple CSV files with IPDR records.
Sales Data Analytics and Insights Tool
Sept 2023 - Nov 2023
Python Development, Data Analysis
DataSearch Analyzer is a powerful search tool with integrated data analysis functionalities, designed to work seamlessly with MongoDB databases. This tool allows users to efficiently search, retrieve, and analyze data stored in MongoDB collections, making it an ideal solution for data exploration and insights.
Data-Science-chatbot
Aug 2023 - Oct 2023
Other
Data-Science Chatbot is a Python-based chatbot project designed to interact with users and respond to various queries related to data science and related topics.
Business Data Analytics with Python and Power BI Dashboarding
Sept 2023 - Oct 2023
Python Development, Data Analysis
Python-based solution for analyzing difffrent databases, fot his case a “CDRs” and presenting the insights through interactive Power BI dashboards.
Text Analysis - Text Chat Bot
May 2023 – Jun 2023
Deep learning
ext Chat Bot is an advanced Python-based system that performs text analysis and simulates a text chat bot. Leveraging libraries like BeautifulSoup for web scraping and data extraction, this project enables users to interact with the chat bot, providing input texts and receiving responses based on the underlying text analysis algorithms.
Power-BI Covid-19 Cases Report-Dashboard
Jan 2022 – Jan 2022
Other, Data Analysis
This project provides a comprehensive Power BI report for visualizing and analyzing Covid-19 cases worldwide. Utilizing Power BI's interactive and dynamic capabilities, this report offers insights into global and regional trends, allowing users to explore and understand the impact of the pandemic.
Neural Network Chatbot with tflearn and NLTK
Oct 2021 – Nov 2021
Deep learning
Built an advanced chatbot using tflearn and NLTK, harnessing the power of intent recognition for precise responses. Streamlined text processing and user interactions, delivering a highly adaptable solution for creating intelligent chat interfaces.
Carbon Emission Analysis and Visualization Impact Project
Duration: Jan 2024 - Jan 2024
Environmental Impact & Data Science
Centered on the pivotal issue of climate change, this project made significant strides in analyzing and visualizing carbon emission data across America, spotlighting the crucial trends of emissions per capita over various years. Through the adept use of SQL for data analysis and PowerBI for visualization, we were not just able to delineate the extremities of carbon emissions by year but also spotlight countries with significant shifts in emissions per capita between 1975 and 2017. This in-depth analysis provided stakeholders with actionable insights to foster targeted environmental policies and interventions.
Dataset Insights: The project utilized comprehensive datasets, including a global carbon emission database sourced from Kaggle and potential emission reduction data from the UN Environment Program, to offer a nuanced view of the environmental challenge.
Research Publications
- Chiranjeev Harshwal (Primary Data Analyst), C Elizabeth Shaaban, Tammy L Dennis. Title: "Mobility and Academic Success of Health Science Postdocs. Status: Paper in progress Note: This project builds upon our earlier research published as "Retention, Mobility, and Successful Transition to Independence of Health Sciences Postdocs"'DOI: 10.1371/journal.pone.0276389'
Contact Informations
- E-mail: chiranjeevharshwal1331@gmail.com
- Phone: +1 412-801-2086