WORK HISTORY
Data Scientist, **/**** to **/****
Amazon - Boston, MA
Senior Data Scientist - Machine Learning(Contract), 11/2018 to 12/2019 Bayer - St. Louis, MO
Data Scientist Intern - Machine Learning, 05/2018 to 08/2018 Monsanto - St. Louis, MO
Research Assistant, 11/2017 to 04/2018
University At Buffalo - Buffalo, NY
Data Scientist – Machine Learning, 02/2016 to 11/2016 Quadratic Insights - Hyderabad, India
CONTACT
Address: Boston, MA 02125
Phone: 716-***-****
Email: adhisp@r.postjobfree.com
WEB LINKS
Github - www.github.com/saikiransunny
Kaggle - www.kaggle.com/saikiranputta
Linkedin - www.linkedin.com/in/saikiranputta
PROFESSIONAL SUMMARY
Result-oriented experienced full-stack Data
Scientist with prior work experience in NLP,
Machine Learning, Deep Learning, and
Econometrics.
Experienced in identifying new ideas and areas
to improve models, engineering, mining large
data sets for insights, building scalable data
products collaborating with a wide range of
stakeholders and cross-functional teams -
Product, Engineering, and Operations and
leading Data Science teams.
SKILLS
EDUCATION
Master of Science, Data Science, 09/2018
University At Buffalo, The State University of
New York - Buffalo
GPA: 3.5/4.0
Bachelor of Technology (B.Tech), Computer
Science, 09/2015
Jawaharlal Nehru Technological University -
Hyderabad, India
GPA: 7.1/10
CERTIFICATIONS
AI For Medicine by deeplearning.ai
SAI KIRAN PUTTA
Built an AI Solution for File System Classification from creating ETL pipeline from raw logs, create model,deploy it resulting in better customer engagement, faster risk analysis and cost analysis.
•
Worked on building several dashboard data products - creating pipelines for data extraction, analysis resulting in improving on-call efficiency by 30%
•
Have also worked on root cause, SLA analysis and create new metrics, KPIs with stakeholders such as product managers that helped Engineering teams to direct their efforts to improve EFS.
•
Built, deployed prediction models for Probability of Purchase, Predictive Order Date, Quantity of Purchase for Bayer's customers improving model's AUC by 10%, RMSE by 12% and RMSE by 5% respectively using external, internal data sources of Bayer. Initiated Stacked Analytics for Customer Segmentation using results from all KPIs with custom distance metrics to run marketing campaigns.
•
Led and mentored a team of three on various customer centricity projects and presented the impact to Business leaders.
•
Designed and implemented system framework in collaboration with Solution Architects for segmentation models from synchronous calls to asynchronous calls resulting in a more robust, secure system.
•
Other responsibilities include, create new metrics and KPIs, leading model reviews, code reviews in absence of Lead Data Scientist.
•
Worked with the Econometrics team on optimizing appropriate discounts for farmers while maximizing profits, market share using Elasticity modeling and Deep Learning techniques resulting in increased profits, market share by 3%, 1.5% respectively.
•
Created new datasets by combining internal, external data sources using rapid application development (RAD) techniques.
•
Have done a project with Prof. Hageman with an objective of improving cluster purity using Deep Learning techniques. The resultant cluster purity improved by over 50%.
•
Built an end-to-end Machine Learning solution for Emotion Classification of Speech for a leading private bank in India with state of the art results, improving the overall addressing time by over 30%.
•
Implemented a end-to-end Machine Learning solution of Email sentiment classification using NLP techniques improving the cumulative addressing time by 2 days.
•
Led a team of interns in medical web scraping and association rule mining of symptoms and side effects of medicines.
•
Experienced in Team Management,
Supervision, Cross-functional collaboration
and Project organization.
•
Proficient in Python, R, Data Science, Machine
Learning, Deep Learning, SQL, Airflow, Kafka,
Spark, Statistics, AWS.
•
Relevant Python Libraries: Pandas, Numpy,
Matplotlib, Seaborn, Sklearn, H2o, Keras,
TensorFlow, Mllib, JobLib
•
Relevant R Libraries: Dplyr, data.table,
Lubridate, ggplot2, Plotly, H2o, Caret, XGBoost,
Glmnet, Rshiny, Parallel
•
Tools: Rstudio, Jupyter Notebook, Git, Domino,
JIRA, Jenkins, AWS Ecosystem (S3, Sagemaker,
Athena, Glue etc)
•