Resume

Sign in

Data Scientist

Location:
Dallas, Texas, United States
Posted:
April 30, 2019

Contact this candidate

Resume:

Tony S John

ac89iv@r.postjobfree.com +1-682-***-**** www.linkedin.com/in/tonysjohn https://github.com/tonysjohn EDUCATION

The University of Texas at Dallas Aug 2018 – May 2020 M.S., Business Analytics GPA – 4/4

University of Kerala May 2009 – May 2013

B.Tech., Electrical and Electronics Engineering CGPA – 3.67/10 TECHNICAL SKILLS

Languages: SQL (Oracle, PostgreSQL, MySQL), Python (NumPy, Scikit-learn, nltk, networkX, geoPandas), R, VBA, UNIX, SAS, PySpark, NoSQL (MongoDB)

Tools: Advanced Excel, MS Access, Tableau, Power BI, QGIS, ArcGIS, Google Analytics, ETL (Alteryx), HDFS BUSINESS EXPERIENCE

Ericsson Aug 2013 – Aug 2018

Senior Data Analyst, Network Analytics - Bengaluru, India

• Assisted clients by creating interactive KPI dashboard and analysis reports using Power BI, Python, Excel.

• Developed 40+ automated data collection and manipulation tools using Excel macros, SQL and shell scripting.

• Performed design, data mining, data analysis and documentation of KPI optimizations performed in network.

• Conducted multiple boot camps in Python, MS Excel, MS Access, SQL to improve team analytical skills. ACADEMIC PROJECTS

Lennox International Data Science Challenge (Alteryx, Python, R, Tableau, ETS) Mar 2019 – Apr 2019

• Identified the factor driving sales conversion happening in HVAC industry; effect of quality KPIs, census data.

• Forecasted category wise sales in 197 plants with 87% accuracy and developed KPI dashboard using Tableau. Retail Scanner Data Analysis (Alteryx, SAS, Tableau, Fixed Effects, Multinomial Logit, RFM) Jan 2019 – Apr 2019

• Analyzed effects of pricing and promotions on weekly product sales from transaction data of 2000+ stores.

• Conducted segmentation analysis, ANOVA and Chi-sq hypothesis tests to conclude pricing strategy. Sentiment Analysis of Social Media Reviews (Pyspark, Flume, Hive, Python, Pandas, Tableau) Jan 2019 – Mar 2019

• Developed Natural Language model to detect user sentiment in twitter reviews with ~83% accuracy.

• Utilized Flume for stream ingestion of live tweets and n-grams, TF-IDF techniques in Big Data framework. Crime in Chicago Kaggle Challenge (Python, Pandas, Numpy, geoPandas, seaborn) Dec 2018 – Jan 2019

• Analyzed and visualized geo-spatial pattern of crime in various zips codes of Chicago. Telecom Customer Churn Prediction (R, ggplot, Lasso, Gradient boosting Machines, SVM) Sep 2018 – Dec 2018

• Evaluated effect of factors like contract type, subscriptions, payment method and customer demographics.

• Improved churn prediction accuracy to 81% using machine learning models like Lasso regression models. AWARDS & ACHIEVEMENTS

• Winner of “Lennox International Data Science Challenge” from among 120+ cross university teams.

• Received "Ace Award" for automating geo-spatial querying of problematic KPI patches using QGIS tool enabling 70% reduced tool usage and 25% faster reporting.

• Received “Power Award” for developing a text scraping tool to parse BSC parameter dumps and highlight discrepancy reducing manhour required by 90%.

LEADERSHIP & ORGANIZATIONS

Intelligence Analytical Society, UT Dallas – Events Officer Aug 2018 - Present

• Organized 12+ networking/workshop events and flagship Analytics Competition with 60+ team participation. Federation of Malayalee Associations of Americas, UT Dallas – Events Officer Apr 2019 - Present



Contact this candidate