· Detail-focused Data Analyst with knowledge in Business Requirements, Functional Specifications, Business Process Flow, Business Process Mapping, data extraction
Masters in Information Technology and Analytics, Dec 2019
Bachelor of Arts, June 2017
Developed and deployed an end-to-end dashboard in Amazon QuickSight, providing real-time visibility into inbound network volumes and flow, enabling stakeholders to make data-driven decisions by viewing information at various granularities.
• Used CHAID analysis on 20,000 ASINs to identify key drivers for cross-docking decisions. The model, developed with a 70/30 test-control split, achieved 77% accuracy, 2e-16 statistical significance, and 0.8026 sensitivity, demonstrating strong performance in detecting positive outcome
• Spearheaded the Low Average Seller Price (ASP) Cost-Saving project, resulting in $356 million in financial savings through strategic cost optimization and financial modeling.
• Streamlined data pipelines and automated data flows from multiple sources, reducing manual reporting efforts by 40% and increasing the efficiency of decision-making processes.
• Collaborated with cross-functional teams to ensure the accuracy and relevance of key performance indicators (KPIs), improving operational transparency and resource allocation.
• Proactively identified data trends and anomalies, leading to a 15% improvement in inbound volume tracking accuracy and enhancing overall logistics efficiency.
• Generated end to end ETL and ELT process using Python and SQL for Data ingestion and transformation in Google cloud platform
• Used BigQuery ML to create and execute demand forecasting models in BigQuery using standard SQL queries
• Developed scripts using Visual Basics, Power Query and Excel to Automate UAT testing, leading to reduction in time taken for data validation from a day to less than 30 minutes.
• Created Sales dashboard in Tableau that provide a comprehensive overview of the business to assist higher management in decision making process.
· Developed data pipelines (ETL) using python (pandas) script to extract and transform CSV data and store into Microsoft SQL Server.
· Designed and built the Database Schema in MS SQL Server Management Studio for data ingestion
· Created interactive dashboard to provide a single glass pane view to analyze top to down performance of the builder business by applying advanced excel tools (Power pivot, OLAP cubes) and macros.
· Developed standardized procedures and predictive algorithms to estimate the value of opportunities and forecast sales using statistical analysis.
· Created email alert system using visual basic which informed sales team about opportunities that are maturing soon.
Project lead for customer database creation using Python:
• Web scraped potential client company’s contact information for targeted marketing from public sources using Selenium (Python)
• Extracted and cleaned client level data using advanced excel tools and techniques
• Enhanced the contact database from 800 contacts to 31000
• Co-developed interactive dashboard using VBA and advanced filters to easily traverse through the database as per the requirements
• Provide analytic insight and recommendations to market clients based on the database.
• Tracked data and developed reports on weekly basis to assess campaign performance
Consultant, Product Quality Complaints Automation for Fresenius Medical Care:
• Developed model using Python for complaint detection, identification and plausible solutions for multiple Fresenius products
• Worked onsite as a client engagement and solutions consultant
• Displayed strong verbal, written skills as well as develop client-ready presentations
• Co-led the offsite technical team to deliver client requirements swiftly and accurately
(Certification No: 280335733OCASQL12C )
Certification No: UC-PXZHLI2I
(Certification No: UC-YQ5BZAFE)
(Certificate Id: ATHM8W2704I6elm2HbUXunNuFgYX)
Cleaned data by removing unwanted columns (review id), all the special characters (! @), single characters from the start, substituting multiple spaces with single space, numbers(0-9) an stop words.
Developed visually interactive exploratory analysis using Plotly Library
Performed NLP tasks like Stemming and Lemmatization
Performed feature Engineering by converting text into count vectors and TF-IDF vectors
Applied Naive Bayes, logistic regression, SVM, decision trees and random forest models on the data set to determine whether the review is helpful or not
Selected the best model, Logistic Regression, based on its AUC-ROC Curve (accuracy not chosen as data was imbalanced)
Applied logistic regression, decision trees and random forest models on the data set to determine whether the person will get admission in the preferred university or not.
Selected the best model, Logistic Regression, based on its 74% accuracy.
Performed K-means clustering to form clusters of students with similar profiles, to suggest student connections.
Applied Multinomial Logistic Regression to make tier-based college suggestions to students.
Used Monte-Carlo Cross Validation to attain reliable estimates for training and testing
Applied Logistic regression, decision trees and random forest models on the dataset to determine whether the person has ASD or not.
Selected Logistic regressions with recall 90.93%; selection was not based on accuracy due to imbalanced data set and high cost of false negative.
Used K fold Cross validation to attain reliable estimates for training and testing
Used google analytics to gather data about visitors, traffic channels and conversion rate; identifying the challenges and making following recommendations:
o Improve Ad effectiveness: Recommended investment in programmatic advertising to enhance digital marketing influence, promising an increase in visits by 25%.
o Drive more traffic: Identified the states that had high unique visitors and goal completion rate and recommended geographical targeting.
o Improve conversion rate: Focus on improving content on social media to bring in unique visitors with chances of higher conversion rates.
Conducted SWOT and Environment Analysis.
Determined the target market as 18-40-year-olds, mainly African Americans and Asian Americans.
Developed targeted marketing plan:
o Incentivised the company with investment opportunities through the suggested minimum balance criteria on the card.
o Focus on stations with multiple modes of transport access (Kiosks and banners advertising).
o Suggested use of Google Ads to target the right customers by choosing appropriate keywords.
Applied logistic regression, decision trees and random forest models on the data set to determine whether the person will get admission in the preferred university or not.
Selected the best model, Logistic Regression, based on its 74% accuracy.
Performed K-means clustering to form clusters of students with similar profiles, to suggest student connections.
Applied Multinomial Logistic Regression to make tier-based college suggestions to students.
Used Monte-Carlo Cross Validation to attain reliable estimates for training and testing.
Organized Travel and Tourism Fest.
Acted as link between students and administration.
Won Zonal and interzonal National Youth Festival Quiz Competition.
Copyright © 2024 Prabhnoor kaur Kahlon - All Rights Reserved.