NEHA MISHRA
**** ** **** ***, **** Lauderdale, FL 333**-***-*** 0912 adkjdg@r.postjobfree.com linkedin.com/in/neha-mishra-2806 WORK EXPERIENCE
Chewy – Data Scientist, Dania Beach Feb 2019 – Present
• Developed Random Forest model for predicting customer's Reorder rate in 60 days with accuracy range of 88-91% and created outreach strategies across customer segments.
• Developed Gradient Boosting model for classification problem of Auto-Ship and uplifted the overall rate of Auto-Ship by 6%.
• Increased share of wallet through cross-sell/up-sell (XG-Boost/GLM) models across multiple products and elevated return on investment (ROI) around marketing strategies by 10%-15%.
• Automated product feeds using Python scripts to ensure ad information is in compliance with the website, to improve customer engagement.
• Improved email engagement by 12% through optimization of communication channels using heuristics, email segmentation models and Optout models.
• Implemented Customer LTV model using Pareto/NBD modelling with an accuracy range of 90-92% to optimize acquisition spending for maximum value rather than minimal cost. Chewy – Data Analyst, Dania Beach July 2018 – Feb 2019
• Automated data pipeline for Digital Marketing channels by fetching performance data from APIs, SFTP using python, DevOps SCM
(GIT), Airflow and thereby reducing effort by 5 hours daily.
• Orchestrated the ETL workflow by optimizing data extraction, data manipulation and data curation making it production ready.
• Automated bid recommendation for paid channels using daily trend, performance to optimize spend and predict best bids for campaign which resulted in decrease of manual effort of 2 hours daily.
• Designed, Evaluated and Built a Marketing Technology Stack (MTA, DMP, DSP, and Identity Resolution Technology).
• Architected solution for one of the major problem areas of segregating mobile app/social cost association with MAI and MAA campaigns and saved thousands of marketing spend.
• Automated the order validation process for Affiliate channel with a python script and API call which accelerated the whole process by reducing manual effort of 3 hours weekly.
SparkCognition – Data Engineer Intern August 2017 – December 2017
• Coded Python scripts to convert input to JSON format to comply with the structure of the PREDIX(GE) environment.
• Benchmarking for Kafka Server using Python Client (Confluent-Kafka-Python).
• Pulled data from OSI Soft PI Server which was used by Data Science team to build models. Finastra (Misys) – Software Engineer Bangalore, IN December 2013 – July 2016
• Re-engineered the legacy Opics (VB) to work on Microsoft .NET technologies, which improved the overall infrastructure.
• Tracked system of salient features of product by customers, region, revenue that resulted in increase of profit by 12%.
• Engineered tool against SQL injection and Cross-site scripting using json-xml based implementation. EDUCATION
Illinois Institute of Technology Chicago, IL
Master of Science in Data Management (GPA-3.9) August 2016 - May 2018 Rajasthan Technical University Rajasthan, INDIA
Bachelor of Technology in Information Technology (GPA-3.5) September 2009 – June 2013 TECHNICAL SKILLS
• Databases/Storage: MySQL, MS SQL Server, Snowflake, Oracle, Kafka, Vertica
• Programming Languages: Python, SQL, R, C#, JavaScript, HTML5, CSS3
• Machine Learning: Clustering, Classification, Forecasting, Recommendation System, Regression, Statistics, Predictive Modeling, Data Mining, Hypothesis Testing
• Data exploration and Visualization tools: Tableau, NumPy, Pandas, Scikit-Learn, Matplotlib, Seaborn, Plotly
• Analytical Tools: Jupyter Notebook, PyCharm, R-Studio, Idle, Weka
• Business Analysis: Business Process Modelling/Design Diagrams, Agile, SDLC, Requirements Elicitations