adjk43@r.postjobfree.com MOTTHILAL BASKARAN +1-480-***-****

github.com/Motthilal Santa Clara, CA linkedin-motthilal-baskaran EDUCATION

MS in Computer Science Arizona State University, USA [CGPA: 3.57/4] May 2020 Coursework: Data Mining, Statistical Machine Learning, Data Visualization, Distributed Database Systems BE in Electronics and Communication Engineering Anna University, India [CGPA: 7.96/10] May 2015 SKILLS

Languages : Python, SQL, R, Scala

Databases : Redshift, Google BigQuery, Postgres, MS SQL Server, MySQL, Oracle, NoSQL Tools & Frameworks : Tableau, AWS-S3, EC2 Instance, Hadoop, Spark, Kafka, Hive, Informatica, Power BI, Docker, ETL, MS PowerPoint, Matplotlib, Seaborn, Docker, Flask, Jupyter, Spyder, MS Excel, VBA EXPERIENCE

ASU Enterprise Marketing Hub Jun’19 - May’20

Data Analyst Assistant (Knowledge & Insights) Tempe, AZ

• Designed and implemented financial stress modelling on financial stress levels of different student categories for stress reduction resulting in 10% stress level decrease.

• Developed GCP framework using foresee API wrapper (Web scraping) to pull survey data that tracks new requests and sends automated email alert about top priority pending requests.

• Instigated and applied LDA topic modelling (using genism, nltk, pyLDAvis) to find top ASU web content with high engagement levels through visualizing insights improved resource engagement by 35%.

• Achieved 30% increase in the authenticity user rate in ASU rewards app through predictive models in R.

• Developed insights using quantitative statistical analysis on which reward categories are popular in ASU rewards app and made recommendations based on the results to add more such categories that improved customer base by 23%. Cognizant Sep’15 - Jul’18

Programmer Analyst Chennai, India

• Built an analytic engine that predicts the on-demand future number of workforces required from historical data and adjustable input parameter as filters increased gross profit by 47%.

• Built and maintained data processing workflows in AWS converting VBA’s from MS Access into SQL queries and showcase the trends in a dashboard.

• Automated data replication from SAPHANA to AWS using python and SQL scripts (2.5 times faster) deployed in AWS EC2 Instances with live monitoring dashboard showing number of transactions per hour.

• Facilitated database migrations from AWS to Big Data clusters using Hive, Impala, Sqoop, Oozie and parquet data format storage for efficient data compression with 0% data loss.

• Transformed several VBA scripts, business logics to SQL queries with performance increase of 33% using sort and distribution keys, column encoding, vacuuming to reclaim unused space and data compression in S3.

• Designed and built ETL pipelines to automate ingestion of over a billion datasets in both AWS and Hadoop environments by creating workflows, data management and data query components. ACADEMIC PROJECTS

Data Visualization of the Amazon dataset [AWS EC2, HTML, CSS, JavaScript, Python, D3.js, NLTK, Tableau] Jan’19

• Implemented intelligent interactive visual analytics of amazon product review dataset (toys) on the usefulness of the ratings and reviews. Performed sentiment analysis and developed word cloud, help meter gauge and time series charts on over 2 million records with 500+ products.

Geo-Spatial Hotspot Analysis [AWS EC2, Hadoop, Spark, Scala, SparkSQL] Jan’19

• Identified statistically significant clusters or outliers by applying spatial statistics on over 2M spatio-temporal ‘New York City Yellow Cab taxi trip records’ data using Getis-Ord statistics approach. CERTIFICATIONS

Applied Data Science with Python [5 course specialization] [Coursera Certification] Jan’20 Visual Analytics with Tableau [Coursera Certification] Jul’20