Akanksha Sharma
Data Scientist with 4 years of experience in building and deploying ML models and data engineering/ETL pipelines with various tools and technologies, including Python, SQL, and cloud platforms. Proficient in implementing data-driven solutions to real-world business problems using Statistical analysis, Data visualization, and Data management.
SKILLS
Data Science: Proficient in building Machine Learning pipelines, experienced in working on Regression Analysis, Time-Series data, Clustering Algorithms, Topic Modeling, Sentiment Analysis, Random Forests, A/B Testing, Scikit-Learn
Data Visualization: Tableau, PowerBI, Excel Dashboard
Programming and Databases: SQL, Python (NumPy, Pandas, sklearn , plotly), R (Tidyverse, ggplot), Seaborn Soft Skills: Effective Trainer, Collaborative Stakeholder Engagement, Cross-Functional Teamwork, Independent Problem-Solver
EXPERIENCE
Quoala Inc – Data Scientist Intern
January 2024 – June 2024
- Worked with cross-functional teams closely to analyzed employee feedback data using Natural Language Processing (NLP) and BERTopic to identify & categorize key topics related to company culture.
- Generated summaries using GPT 3.5 Turbo that tracked cultural trends over time, resulting in a 20% increase in efficiency in identifying areas for improvement.
CDWG – Data Scientist/Engineer Intern
January 2024 – June 2024
- Led a team of 4 to design and implement an Azure data pipeline using Python for automating market research for Space Force.
- Developing & implementing the ETL pipeline to scrape, clean, and transform web data for opportunity identification in Azure.
- Developed a PowerBI Dashboard for stakeholders to see all the scraped data’s insight at one place and find bidding opportunities.
Gearsim – Data Science Intern
July 2023 – September 2023
- Developed a Flask-based app for generating data profiling reports by uploading CSV files, reducing report generation time by 80%.
- Conducted hypothesis testing on United Airlines’ Flight Delay dataset, resulting in a 15% reduction in flight delay prediction error.
- Created a predictive model for landing gear force on airplane legs during landings, achieving an R-squared value of 0.85.
- Developed a Streamlit-based frontend application for real-time predictions, improving operational efficiency by 20%.
Syniti – Senior Data Consultant
January 2020 – August 2022
- Implemented a real-time support ticket routing system using Logistic Regression and Decision Trees, reducing response time by 95% (from 20 to 1 min/ticket) with 98% accuracy of ticket classification based on severity.
- Developed comprehensive data profiling reports to ensure the accuracy, completeness, and consistency of master data for financial entities such as Business Partners, Purchase Orders, and Configure, Price, Quote (CPQ) processes.
- Processed data in Alteryx to create TDE for tableau reporting. Generated various Monthly, Quarterly, Bi-Yearly, Yearly reports by - different type of reports using Tableau.
- Developed, reviewed, debugged, tested, and deployed SSIS packages using SQL Server to streamline data integration processes. - Owned and led new hire technical training and demo project mentoring. Trained 40+ new hires in a span of six months
Wipro – Data Engineer
July 2018 – January 2020
- Led the data migration from Mainframe to HANA by creating structured de-normalized ERP (Enterprise Resource Planning) datasets, reducing manual effort by 93% (from 12 to 1 HC/year).
- Automated data cleaning, validation, and data quality checks during data migration using Regex, Dedup, and Pandas, decreasing the processing time by 97% (from 100 to 4 hrs) for each data migration cycle, consisting of at least 1B+ data records.
- Developed executive-level project status Tableau dashboards for milestone status, blockers/risks, and call to action focus areas.
Grozip - Intern
December 2016 – January 2017
- Designed and launched a chatbot on the Facebook Messenger platform for real-time customer support and product search functionality, improving referral traffic by 54%.
- Led the redesign of data lake architecture for a new web application during migration, using an Entity-Relationship (ER) diagram resulting in efficient data retrieval and reduced deduplication by 75%.
- Designed a targeted campaign framework, using Google Analytics, to identify focus regions based on website traffic and user behavior for sales and marketing teams, increasing revenue-per-sale by 60%.
EDUCATION
- Seattle University
- MS in Data Science (September 2022 – Present)
- CGPA: 3.93/4 (4x Dean’s Honor List)
- Relevant Coursework: Statistical Inference, A/B Testing, Data Visualization, Text Processing, Big Data & Analytics.
- VIT University
- B.Tech - Computer Science and Engineering (2014-2018)
- CGPA: 8.90/10
- Relevant Coursework: Cloud Computing, Software Engineering, Data Structures & Algorithms, Algorithm Design, Agent-based intelligent systems.