Hello! I'm Arjun Ananda Padmanabhan, a dynamic professional with a rich blend of expertise in business administration, health informatics, and clinical experience. A graduate of the University of Michigan, I've developed a keen acumen in both the healthcare and business sectors. My career path showcases a strong track record in leadership roles, innovative problem-solving, and a passion for integrating technology into healthcare and business strategies. Currently, I leverage my diverse skill set to create impactful solutions in sustainability, operational effectiveness, and market research. I'm deeply committed to driving positive change and excellence in every endeavor I undertake.
- Masters in Business Administration (August 2021 to May 2024)
- Masters in Health Informatics (August 2021 to May 2024)
- Bachelor of Dental Surgery (August 2012 to September 2016)
- Developed and executed comprehensive recruitment strategy, leading to 30% increase in qualified applicants and 20% reduction in time-to-fill positions
- Implemented deep learning algorithms to analyze robust customer data, increasing brand value by $1M and improving targeted marketing campaigns by 15%
- Collaborated with cross-functional teams to streamline processes by integrating AWS (Lambda, S3, RDS) and Salesforce platforms, leading to 50% increase in overall operational effectiveness by automating manual process and reducing turn around time
- Developing a tailored carbon emission (Scope 3) calculation model to assist a Fortune 50 electric vehicle and industrial equipment manufacturer in achieving their 2025 sustainability objectives
- Mapping LCA of battery value chain, and system boundaries from raw material aquisition to battery manufacturing
- Facilitated SI 618 and SI 370: Data Analysis and Manipulation, guiding students in mastering complex data analysis techniques using Python and SQL, and fostering practical skills in data manipulation, visualization, and interpretation to solve real-world problems.
- Actively engaged in curriculum development, leading interactive sessions, and providing personalized feedback and support to enhance student learning outcomes.
- Conducted extensive market research and analysis to assess feasibility of establishing new social venture centered on heat pump sales in Anchorage, projected potential revenue increase of $500K within the first year
- Performed comprehensive breakdown, statistical analysis for energy-efficient solutions, identifying potential cost savings of up to 20% for potential customers and estimated customer conversion rate increase of 15%
- Developed detailed financial projections and business models that demonstrated long-term profitability and sustainability of proposed social venture. These projections showcased potential return on investment (ROI) of 25% within three years
- Designed and launched Quality Management Dashboard for product team saving company 15% in operating expenses, about $20K/month
- Implemented and customized data automation process for medical team, optimizing processing efficiency, resulting in 25% reduction in operational expenses, 15% increase in data quality, and 15% improvement in workflow efficiency
- Developed and deployed machine learning algorithms for $250K project, to predict quality of life in patients with Huntington's disease to aid in treatment decisions and outcomes
- Partnered with 10+ clinical professionals to streamline data collection process, enhancing quality of data by 20%
- Developed and implemented in-house iPatientCare Electronic Health Record (EHR), replacing third-party software and resulting in a 20% reduction in expenses, ~ $250K/year
- Deployed 8 client implementations over 3 month period, generating $4M in revenue
- Managed team of 12 clinical documentation specialists and 3 quality analysts, completing 100% of projects on time and within budget
- Developed team processes, that yielded 25% reduction in training time for new employees while maintaining 100% staff retention rate
- Mentored ~150 staff in EHR navigation, across 15 training sessions that led to a boost in abstraction output by 60%
- Piloted a project for prospective client and secured a $2M deal after concluding early
- Reviewed and calibrated auditing tools for chart review following a set of 17 criteria; inspected and calibrated chart note to ensure they satisfy the requirements of specified standards or performance
- Mentored 10 team members, teaching them customer preferences and how to conform to the set norms of their respective physicians. By incorporating 80 smart phrases, we were able to reduce production time for generating a single chart history by 30% while increasing team total output by 60%
- Gained diverse experience across various dental departments, managing complex cases with skill and precision.
- Actively participated in numerous trauma surgeries, contributing to critical surgical procedures.
- Successfully treated approximately 1,000 patients annually, demonstrating proficiency in patient care and dental treatment.
This project is an intricate analysis of the U.S. presidential debates between Donald Trump and Joe Biden. Employing advanced Natural Language Processing (NLP) techniques, the aim was to unravel the complex layers of linguistic patterns, sentiments, and communication tactics used by the candidates. The project involved meticulous data preprocessing of debate transcripts, application of NLP methods like tokenization, stopword removal, stemming, and lemmatization, and a robust quantitative analysis of word usage. Sentiment analysis was a key component, assessing the emotional tone and underlying sentiments of each candidate's speeches.
The methodology encompassed Python programming, leveraging NLP libraries such as NLTK and Spacy, and data manipulation with Pandas and NumPy. The visual representation of data was achieved using Matplotlib and Seaborn, which helped in interpreting and comparing the linguistic data effectively.
This project objective is to forecast the survival outcomes of the Titanic passengers by utilizing machine learning techniques to analyze and predict based on historical data. The project began with a meticulous phase of data preparation, where data was cleaned and exploratory data analysis (EDA) was conducted on the Titanic dataset. This initial phase was crucial for understanding the data's intricacies and laying the foundation for accurate predictive modeling.
The analytical part of the project involved the strategic application of various classification algorithms. Range of models were employed such as Logistic Regression, Support Vector Machines, and Random Forest classifiers, each offering unique strengths in handling the intricacies of the Titanic dataset. A significant portion of the project was dedicated to hyperparameter tuning and cross-validation to optimize the models' performance.
In this project, sophisticated web application were created using Flask, a Python web framework, designed to provide detailed information about movies and TV shows. This application offered a user-friendly interface for querying based on language, genre, and year, and displayed extensive data such as descriptions, popularity scores, and IMDb ratings. The backend was powered by an SQLite database, structured to efficiently store and manage diverse movie and TV show data. For data collection, I used Python's Pandas library to process CSV files, and integrated The Movie Database (TMDb) API for real-time data retrieval, including fetching IMDb IDs and poster images. Additionally, web scraping techniques were implemented to gather actor images from Wikipedia, enhancing the richness of the information presented.
Skills demonstrated in this project are web application development with Flask, database management with SQLite3, data processing and visualization, and API integration. It also involved crafting complex SQL queries to handle user searches and presenting results in an engaging format using HTML and CSS.
In this project, deep learning techniques were utilized to analyze and compare the sentiments expressed in COVID-19 related tweets from politically distinct Red and Blue states. The project involved collecting a large dataset of tweets using API (SNS Scrape), which were then categorized based on the geographic location of the users to identify the political leaning of each state. Employing advanced NLP methodologies, I processed and normalized the textual data, preparing it for deep learning analysis.
The sentiment analysis was conducted using a sophisticated model, incorporating BERT model, adept at capturing the contextual nuances in the tweets. This approach enabled a nuanced comparison of public sentiment across different political landscapes during the pandemic. The results, visualized through compelling data visualizations, offered insightful perspectives on how public opinion varied in response to COVID-19 across the political divide.
Served as an Investment Fellow in the Tuner MIINT program, conducting in-depth market research, financial analysis, and due diligence for potential investment opportunities in emerging markets.Collaborated with a team to evaluate and present investment recommendations to a panel of experienced investors, focusing on high-impact ventures with sustainable growth potential.
Actively participated in the International Investment Fund at Ross School of Business, focusing on identifying and evaluating promising startups in India and Africa. Conducted comprehensive market analysis, financial modeling, and due diligence to assess investment viability and potential for high returns.Collaborated with a diverse team to develop investment strategies, contributing to the fund's mission of fostering growth and innovation in emerging markets.