You are on page 1of 11

Venkat 

Korapati Vishal
Phone: +12146991732
Home: -
Email: venkatkorapativishal@gmail.com

RESUME   

Resume Headline: StructuredProfile-db9a298d-9210-48b4-aaea- Resume Value:


71be2e7d7891 wfm6yjnat4yyff9m   
  

OBJECTIVE: Machine Learning Engineer with more than 9 years of experience in


all aspects of the data science project life cycle, including modeling,
inferential statistics, data validation, deployment, and monitoring. In
those 5 years as NLP Engineer implementing end-to-end big data-
based analytical solution and handling large-scale unstructured data.

* Overall 9 years' experience in Data Extraction, Data Modelling, Data


Wrangling, Statistical Modeling, Statistical Analysis, Data Mining,
Machine Learning and Data Visualization, artificial Intelligence/Deep
Learning
* Domain knowledge and experience in Retail, Banking and
Manufacture industries
* Proficient in Python 2.x/3.x with SciPy Stack packages including
NumPy, Pandas, SciPy, Matplotlib and IPython
* Knowledge and experience with AWS services (S3, Glue, Redshift,
Quicksight, Sagemaker, Lambda)
* Developed predictive models using Decision Tree, Random Forest,
Naïve Bayes, Logistic Regression, Cluster Analysis, and Neural
Networks.
* Proficient in applying Statistical Modelling and Machine Learning
techniques (Linear Regression, Logistic Regression, Decision Trees,
Random Forest, SVM, K - Nearest Neighbors, Bayesian, XG Boost) in
Forecasting/ Predictive Analytics, Segmentation methodologies,
Regression based models, Factor analysis, PCA, Ensembles and good
knowledge on Recommendation Systems
* Hands on experience in implementing LDA, Naive Bayes and
skilled in Random Forests, Decision Trees, Linear and Logistic
Regression, SVM, Clustering, neural networks, Principal Component
Analysis and good AWS knowledge on Recommender Systems.
* Proficient in managing entire data science project life cycle and
actively involved in all the phases of project life cycle including data
acquisition, data cleaning, data engineering, features scaling, features
engineering, statistical modeling, testing and validation and data
visualization.
* Proficient in Machine Learning algorithms and Predictive Modeling
including Linear Regressi

EXPERIENCE: 8/2021 - Present UBS


Senior Machine Learning Engineer

Responsibilities:* Implemented personalized and recommended


system features and developed a knowledge-enabled personalization
algorithm for the homepage and entity recommendation application.*
Worked with Kubernetes to deploy, scale, and operate application
containers across clusters of hosts.* Designed and implemented
deployment strategies and CI/CD pipelines using GitHub Actions*
Predicted customer intent by building a LSTM model based on click
events to personalize the customer experience* Built and monitored
dashboards to visualize pitfalls and lower the drop-off rate at checkout
resulting in an increase in annual revenue* Led end-to-end project
work, including data collection, model development and execution,
interpretation of model results, and engagement with key business
stakeholders* Increased digital sales by improving e-commerce
customer experience on the website through Personalization &
Targeted Promotions resulting in increase in online orders* Developed
Spark Code using Spark SQL, Data Frame and Spark Core API for
aggregation and report generation* Performed an exploratory data
analysis approach to verify potential AI/ML use cases* Redesigned
various aspects of digital ordering flow by identifying procedural
areas for improvement* Analyzed Customers data for Market
Segmentation & Target promotions, built models that improved 5G
business profits, Sales, and Service on the e-commerce platform*
Utilized GCP resources Big Query, compute engine, Kubernetes
cluster and GCP storage buckets for building the production ML
pipeline Enterprise Data Platform. Including establishing connection
between Azure Resources (ADF, Databricks, ADLS GEN2, Storage
layer access for ADF)* Deployed a spam detection model and
performed sentiment analysis of customer product reviews using NLP
techniques.* Engineered cutting-edge Machine Learning and NLP
technologies to drive core business* Responsible to build an Azure
Cloud Enterprise Data Platform. Including establishing connection
between Azure Resources(ADF, Databricks, ADLS GEN2, Storage
layer access for ADF)* Created custom SQL queries in Teradata SQL
Workbench to prepare datasets for Tableau dashboards* Leveraged
metrics derived from various data sources and built models that
increased 5G business profits leading to an increase in order
conversion rate* Performed across multiple functional departments,
translating business problems into solvable cases, with emphasis on
anticipating future ad-hoc needs* Established strategy dashboards and
charts to inform and compile multiple strategies, market, and user
insights, improving data visibility by 45%* Performed NLP by using
techniques like Word2Vec, FastText, Bag of Words, tf-idf, Doc2Vec*
Explored and analyzed the customer-specific features using Spark
SQL* Optimized Performance through Spark Tuning and Query
Optimization* Conducted analysis to assess customer behaviors and
discovered the value of customers with

6/2019 - 7/2021 Verizon Wireless


Machine Learning Engineer

Responsibilities:* Participated in all phases of critically important


Machine Learning and Deep Learning projects requiring complex
custom models* Designed and executed A/B tests to determine the
efficacy of email, and web marketing campaigns. Tracked KPIs using
Google Analytics and Adobe Site Catalyst* Deployed trained models
using Flask REST APIs and built Flask web applications to consume
these models. Built Docker containers, and WSGI to serve these web
applications* Extracted transaction data of all 11 big territories (1
million+) by PySpark and analyzed the data to forecast the areas
(SkLearn/MLLib) with higher revenue in a 95% accuracy rate.*
Performed market analysis to efficiently achieve objectives, increasing
portfolio and customer Base by approximately 17% and 6%
respectively.* Implemented dimensionality reduction techniques like
PCA, LDA by applying feature selection and feature extraction.*
Experience in Natural Language Processing (NLP) and Time Series
Analysis and Forecasting using ARIMA model in Python and R.*
Implementing various machine learning algorithms on large volume of
data in PySpark using MLLib.* Performed Cross-validation for model
validation, tested against test data, and leveraged automated
hyperparameter tuning techniques such as grid search / sweep,
changed models when necessary* Handled bias and variance trade -
off, evaluating model fit with appropriate measures of chosen
algorithms* Led the team in developing scalable tools using Machine
Learning and Deep learning algorithms to predict customer behavior
to improve their experience on digital platform* Collaborated with
data engineers and operation teams to implement ETL processes,
writing and optimizing SQL queries for data extraction to meet
analytical requirements* Conducted univariate and multivariate
analysis on data to identify underlying patterns and associations
between variables* Designed, built and deployed Python modeling
APIs for customer analytics, integrating machine learning techniques
for customer behavior prediction* Created and implemented a
research proposal for the analysis of customer reviews using NLP
techniques.* Built a propensity model to determine the likelihood of a
customer abandoning a product in their cart and purchasing the same
product from an assisted channel, such as a store* Created research
design and analysis based on identified needs, analyzing internal or
3rd party data sources in response to data analysis request to meet
business requirement* Conducted data cleaning ensuring data quality,
consistency, and integrity using Pandas, and Numpy* Evaluated
model performance using metrics such as RMSE score, confusion
matrix, ROC, cross validation and A/B testing to in both simulated
environment and real world* Used Selenium Python scripts to extract
desired data from a given URL in an automated way* Tackled highly
imbalanced datasets using oversampling with SMOTE and cost-
sensitive algorit

8/2016 - 5/2019 Zara


Data Scientist

Responsibilities:* Developed and implemented a Chatbot on the web


that utilized Multilabel classification model, Anomaly Detection, and
Customer chat modeling to reduce the call time.* Deployed trained
Machine Learning solutions through Batch Execution Web Services in
Python API Web Services, enabling efficient and effective utilization
of machine learning models* Involved in developing a Map Reduce
framework that filters out bad and unnecessary records enhancing data
quality and improving analysis outcomes.* Utilized Spark-SQL to
load data and create schema RDD, which was then loaded into Hive
tables, enabling efficient querying and analysis of large datasets*
Developed python scripts to analyze server log files, improving speed,
accuracy and performing root cause analysis of critical application
failures* Explored and analyzed the customer specific features by
using Matplotlib in Python.* Wrote Map Reduce code that takes log
files as input, parsing and structuring them in tabular format to
facilitate effective querying and analysis of log data* Performed ad-
hoc data preprocessing tasks such as outliers detection/removal, and
elimination of multi-collinearity using Principal Component Analysis
(PCA) through Python scripting* Collected and synthesize business
requirements to create effective machine learning use cases that meets
the organization needs and enhanced business outcomes.* Developed
machine learning models using Google TensorFlow Keras API for
Classification problems, fine-tuning model performance by adjusting
the epochs, batch size, and optimizer improving model effectiveness*
Played a key role in setting up the CI/CD pipeline using GitHub,
facilitating effective deployment of models* Utilized PCA and other
feature engineering techniques to reduce high-dimensional data,
applied feature scaling, and handled categorical attributes using the
one-hot encoder of Scikit-learn library* Worked with Python libraries,
including NumPy, SciPy, Pandas, Matplotlib, Stats packages to
perform dataset manipulation, data mapping, data cleansing and
feature engineeringEnvironment: Classification Algorithms, Anomaly
Detection Algorithms, Web Services, Map Reduce Framework, Hive,
Python, Keras, GitHub, Scikit-Learn, SciPy, Pandas, NumPy, Shell
Scripting, MySQL, Stats packages

3/2013 - 7/2016 UBER


Data Science Analyst

Responsibilities:* Worked in Agile Scrum Methodology with daily


stand-up meetings, great knowledge working with Visual SourceSafe
for Visual studio 2010 and tracking the projects using Trello*
Generated Drill through and Drill down reports with Drop down menu
option, sorting the data, and defining subtotals in Power BI*
Participated in feature engineering such as feature intersection
generating, feature normalize and label encoding with Scikit-learn
preprocessing* Used various metrics (RMSE, MAE, F-Score, ROC
and AUC) to evaluate the performance of each model* Conducted
Data blending, Data preparation using Alteryx and SQL for tableau
consumption and publishing data sources to Tableau server*
Developed stored procedures and triggers to facilitate consistent data
entry into the database* Good working knowledge on Developing
Aggregation, KPIs, Measures, Data Mining Models and Deploying*
Experience in creating Ad hoc reports and reports with complex
formulas and to query the database for Business Intelligence* Raised
10% of revenue by lowering False Positive and False Negative by
applying Bagging and Boosting algorithms.* Extracted social media
data, crunched and built word clouds, data graphs and story boards
using Power Bi to provide in-depth story analysis and provided
recommendations* Improved data cleansing and mining processes
based on SQL, resulting in a 50%-time reduction.* Expertise in
developing Parameterized Chart, Graph, Dashboard, Scorecards, Drill-
through and Cascading reports using Power BI* Leveraged tweets to
devise a grievance analysis model that facilitated in providing
intelligent insights pertaining to Location and Complaints/Issues for
aiding Grievance Management* Worked on extracting the review
from Google sites to provide the company customer feedback to data
subjects through python automation jobs* Consumed Adobe analytics
web API and written the python script to get the consumer journey
report for the analysis* Prepare detailed test cases for Site Catalyst
tracking requirements* Tuning queries which are running slow using
Profiler and Statistics by using different Methods in terms of
evaluating joins, indexes, updating Statistics and code
modificationsEnvironment: Power BI, Python, MS Office, SharePoint,
Jira, PyCharm, Tableau, Azure Machine Learning, Adobe Analytics,
Teradata, Scikit-Learn, Tweepy, NLTK, Agile Scrum Methodology,
Trello, Alteryx, SQL

EDUCATION: Stevens Institute of


Technology
Master's Degree
* Master's in Information Systems from Stevens Institute of
Technology

SKILLS: Skill Name Skill Level


GCP Unspecified
HTML Unspecified
XML Unspecified
.Net Unspecified
Microsoft Office Unspecified
Microsoft Powerpoint Unspecified
Microsoft SharePoint Unspecified
Microsoft SQL Server Unspecified
Apache Unspecified
Artificial Intelligence Unspecified
Change Management Unspecified
CSS Unspecified
Data Analysis Unspecified
Data Entry Unspecified
Data Mining Unspecified
Data Modeling Unspecified
Data Warehousing Unspecified
database Unspecified
erwin Unspecified
ETL Unspecified
excel Unspecified
Forecasting Unspecified
Informatica Unspecified
Java Unspecified
JSON Unspecified
MAC Unspecified
Mac OS Unspecified
Market Analysis Unspecified
Market Segmentation Unspecified
Marketing Unspecified
Marketing Analysis Unspecified
ms office Unspecified
MS SQL Server Unspecified
MySQL Unspecified
Object-Oriented Unspecified
Programming
Oracle Unspecified
PowerPoint Unspecified
Project Management Unspecified
purchasing Unspecified
Python Unspecified
Requirements Analysis Unspecified
Retail Unspecified
SCRUM Unspecified
SDLC Unspecified
SharePoint Unspecified
Shell Scripting Unspecified
Software Development Unspecified
Life Cycle
SQL Unspecified
SQL Server Unspecified
Statistical Analysis Unspecified
Statistics Unspecified
Stored Procedures Unspecified
Teradata Unspecified
Visual Studio Unspecified
Web Services Unspecified
Algorithm Unspecified
Apache Spark Unspecified
API Unspecified
Continuous Unspecified
Integration/Delivery
CI/CD Unspecified
Git Unspecified
Visualization Unspecified
Business Requirements Unspecified
Collection Unspecified
Neural Unspecified
Blending Unspecified
Test Cases Unspecified
Verizon Unspecified
Encoding Unspecified
Sorting Unspecified
Publishing Unspecified
Translated Unspecified
Translating Unspecified
Issue Management Unspecified
Buying/Procurement Unspecified
Ordering Unspecified
Pipeline Unspecified
Neural Network Unspecified
Root Cause Analysis Unspecified
Encoder Unspecified
Segmentation Unspecified
Retail Marketing Unspecified
Data Extraction Unspecified
Learning Solutions Unspecified
Metrics Unspecified
Business Plans Unspecified
Customer Behavior Unspecified
Google Analytics Unspecified
Business Intelligence Unspecified
Statistical Modeling Unspecified
Audience Unspecified
Segmentation
Ecosystem Unspecified
Parsing Unspecified
Scala Unspecified
Eclipse Unspecified
Frameworks Unspecified
Data Acquisition Unspecified
Wireless Unspecified
Optimization Unspecified
Data Structures Unspecified
Large-Scale Unspecified
REST Unspecified
WEB API Unspecified
Streaming Unspecified
Data Validation Unspecified
HP Unified Functional Unspecified
Testing
UFT Unspecified
Selenium Unspecified
Deployment Unspecified
Catalyst Unspecified
Asteradata Unspecified
Compute Engine Unspecified
Docker Unspecified
Google Cloud Unspecified
Kubernetes Unspecified
Data Quality Unspecified
USE Cases Unspecified
Tableau Software Unspecified
Tableau Unspecified
GitHub Unspecified
Amazon Web Services Unspecified
AWS Unspecified
Agile Unspecified
Agile Methodologies Unspecified
JIRA Unspecified
Version Control Unspecified
Dimensional Data Unspecified
Life Cycle Unspecified
PCA Unspecified
PyTorch Unspecified
Random Forest Unspecified
Random Forests Unspecified
Support Vector Unspecified
Machine
SVM Unspecified
Linear Discriminant Unspecified
Analysis
Linear Regression Unspecified
Logistic Regression Unspecified
Naïve Bayes Unspecified
Neural Networks Unspecified
Principal Component Unspecified
Analysis
Boosting Unspecified
Decision Trees Unspecified
Deep Learning Unspecified
Dimensionality Unspecified
Reduction
Factor Analysis Unspecified
K-Nearest Neighbor Unspecified
Database Modeling Unspecified
Postgres Unspecified
SQL Queries Unspecified
Analysis of Variance Unspecified
Anova Unspecified
Anomaly Detection Unspecified
Tableau Server Unspecified
Transaction Data Unspecified
Unstructured Data Unspecified
Data Cleaning Unspecified
Data Mapping Unspecified
Data Transformation Unspecified
Nosql Unspecified
Power Bi Unspecified
Predictive Analytics Unspecified
Predictive Modeling Unspecified
Sentiment Analysis Unspecified
Star Schema Unspecified
LDA Unspecified
Machine Learning Unspecified
MAP Reduce Unspecified
Mongodb Unspecified
Natural Language Unspecified
Processing
NLP Unspecified
Data Visualization Unspecified
Datasets Unspecified
Hadoop Cluster Unspecified
Hadoop Distributed Unspecified
File System
Kafka Unspecified
Latent Dirichlet Unspecified
Allocation
Clustering Unspecified
Collinearity Unspecified
Data Cleansing Unspecified
Data Collection Unspecified
Data Science Unspecified
Data Sources Unspecified
Visual Sourcesafe Unspecified
Apache Hadoop HDFS Unspecified
Apache Hadoop Unspecified
Mapreduce
Bayesian Unspecified
Big Data Unspecified
Cassandra Unspecified
Pycharm Unspecified
Pyspark Unspecified
Tensorflow Unspecified
Real Time Unspecified
Scripting Unspecified
Shiny Unspecified
Flask Unspecified
GGPLOT2 Unspecified
Keras Unspecified
Matplotlib Unspecified
Numpy Unspecified
Pandas Unspecified
Hadoop Unspecified
Hbase Unspecified
HDFS Unspecified
Hive Unspecified
Mapreduce Unspecified
Object-Oriented Unspecified

LANGUAGES: Languages Proficiency Level


English Intermediate

Additional Info  
Work Status: US - I am authorized to work in this country for any employer.
Active Security Clearance: None

Target Job: Target Job Title: Data Scientist

Target Locations: Selected Locations: US-TX-Dallas


Relocate: No
Willingness to travel: No Travel Required

You might also like