VINNAKOTA SAMHITA

+91-831******* adc47h@r.postjobfree.com Bangalore

CERTIFIED DATA SCIENTIST

Certified Data Science Professional highly skilled in Analytics, Mathematics and Statistics. Proficient in R, SAS, Python,Tableau. Hands on experience on R, Python

TECHNICAL SKILLS

CERTIFICATIONS AND TRAINING

KEY DATA SCIENCE PROJECTS

Project: Banking Tech Stack : R

Project: Manufacturing Tech Stack : R

Project: Consumer Complaints Resolution Tech Stack : Python Machine Learning: Linear Regression, Logistic Regression, Decision Tree, Random Forest, Boosting machines, XGboost, Segmentation and Clustering, Time series analysis

Language: R, SAS, Python, C, C++, Java, SQL

Platforms: Windows, Ubuntu

Tools: Tableau Desktop, Anaconda, SQL Server

Certified Data Science Specialist Edvancer Eduventures Aug '18 - Mar '19 R, Python, Tableau, SAS, SQL Software testing course Testing Campus Infotech Mar '18 - June '18 Manual testing, Core Java, Selenium, SQL, Agile Online Summer Course for Android Internshala Jul '16 Core Java basics, Android basics Objective : A bank was rolling out a new term deposits product and wanted to predict which of their existing customers to target as part of maximizing ROI

Solution : Deployed Logistic regression to create a propensity model in R language to predict those customers most likely to respond positively to the new product and the campaign Key Achievement : Achieved a model accuracy of 80% and AUC of 90% Objective : Part backorders is a common supply chain problem and wanted to identify parts at risk of backorder before the event occurs so the business has time to react

Solution : Deployed random forest to predict whether the product actually went on backorder or not Key Achievement : Concluded a reduction in average waiting time from 10 days to 3 days Objective : Consumer complaint resolution is important to any business. In this particular case we have been given detailed consumer complaints along with whether consumer disputed with the conclusion. If we are able to predict this, consumer who is more likely to dispute a conclusion can be given more attention as to how the complaints are handled as well as how persuasively the final conlusions are conveyed to them Solution : Deployed Random forest to predict which consumer is more likely to dispute the resolution of a complaint Key Achievement : Achieved a model accuracy of 70% Project: Counterfeit Medicines Sales Prediction Tech Stack : Python Project: Data Visualization Project Tech Stack : Tableau We have the data which contains building city, building state, building status, property type, total parking spaces, owned/leased. We need to find the answers for the following questions: 1. How is the overall situation of total parking spaces by a) Owned/Leased

b) Property type

c) Within each property type how is owned and leased d) By building status

e) By building state

2. In which building state parking situation is in excess 3. In which type of property parking space is in excess EDUCATION

CMR Institute of Technology

Bachelors in Information Science Bengaluru, IN Jul '13 Jun '17 Narayana Junior College

Board of Intermediate Vijayawada, IN Jun '11 May '13 Sri Chaitanya Techno School

Secondary Education Board Kakinada, IN Jun '10 Apr '11 ADDITIONAL INFORMATION

LANGUAGES : Proficient in English, Telugu and Hindi. Understanding skills in Kannada Objective : Counterfeit medicines are fake medicines which are either contaminated or contain wrong or no active ingredient. They could have the right active ingredient but at the wrong dose. Government has decided that they should focus on illegal operations of high net worth. In order to do that they have collected data which will help them to predict sales figures given an illegal operation's characteristics.

Solution : Created a Random Forest model to predict counterfeit medicine sales and pinpoint high value operators

-

-

-

Contact this candidate