SUMMARY

• Data Scientist with 6+ years of experience executing data - driven solutions to increase efficiency, accuracy and utility of internal data processing.
• Experienced at creating data regression models, using predictive data modeling, and analyzing data mining algorithms to deliver insights and implement action-oriented solutions to complex business problems.
• Experienced at client facing roles in alternative credit scoring, automated chat-bot, stock price prediction, churn prediction and prevention, loyalty modeling, anomaly detection for telecom, fraud analytics for financial services and predictive maintenance.
• Worked on Big-Data platform using python(pyspark), R(sparkr) and sql(sparksql).

TECHNICAL SKILLS

Languages: Python, R, SQL, Hadoop, Spark, Hive, Matlab, Java script, C.

Libraries: Tensor flow, Pandas, Numpy, Scikit Learn, Keras, Caffe, PyTorch.

Visualization tools: Tableau, QlikView, Excel

Databases: NoSQL, Hbase, MongoDB, Radis, Oracle.

Methodology: Agile(Scrum), DevOps

Repositories: Git, Bit Bucket

Container: Docker.

Operating System: Linux, Unix

Domains: Telecommunication, Finance, Retail, Digital and E-Commerce.

PROFESSIONAL EXPERIENCE

Senior Data Scientist

Confidential

Responsibilities:

• Developed credit risk models that will determine loan eligibility, as well as repayment/ default predictions.
• Feature Engineering from Browsing Behavior, Call detail record and Payment Information.
• Roll-rate analysis for Bad flag definition.
• Development of predictive models that will determine pricing and interest rates.
• Took an active role in monitoring and adjusting all models.
• Performed ad-hoc reporting and analysis, when needed.
• Work with marketing and advertising teams to determine the best way to target potential clients.
• Alternative credit risk modeling from Telecom (True Corp. ), Retail (Makro and 7-Eleven) and electronic wallet (True money) data.
• Churn prediction model for Contract expiry in Postpaid customer base.
• Prepaid to Postpaid migration lead generation for revenue upscale and enhance customer loyalty.
• Worked for Handset finance loan based to previous telecom, retail and electronic wallet usage.
• Worked on statistical modeling for dynamic airtime advance (micro lending) for prepaid customers.
• Build recommendation engine to propose next best offer for prepaid customer based on previous top-up and topping patterns.

Data Scientist

Confidential

Responsibilities:

• Worked with a team of applications system engineers and business analysts, while partnering closely with multiple lines of business, WF Chatbot/ Virtual assistant and machine learning development, test engineers and a wide range of other teams involved working on the release.
• Develop model as a service to enable NLP API’s for integration with other banking internal systems and front end channels such as Confidential USA, teamwork etc.
• Implement tools and best practices for release, environment, and configuration management to improve deploy success rates. This includes the new SDLC process and enterprise bar tools.
• Act as strong advocate for quality and reusability in the services.
• Provided direction and guidance to less experienced staff, requires hands on development and experience leading a small team of developers.
• Adopt to leverage enterprise architectural principles, including SEA.
• Work closely with agile scrum master, contribute in scrum ceremonies such as the sprint planning meeting, daily scrum, sprint review meeting, and sprint retrospective meeting.
• Active participation in artifacts such as product increment, product backlog, sprint backlog and lead end of sprint demo to all key scrum stakeholders.

Data Scientist

Confidential

Responsibilities:

• Creation of models for planification and technology (smart capex, churners, detractors, service degradation, etc.)
• Research and definition of the KPI's and thresholds associated to user perception (TNPS) for different mobile services (video, web, voice, VoLTE, etc).
• Tune-up and exploitation of the world's first complete CEM big data implementation for telecommunications
• Analysis of Confidential detractors and guidance to the technical departments in order to be the best mobile network in Spain during all the years in charge of that task.
• Worked with a team of data scientists and analysts who work in squads together with data engineers and quality assurance engineers to generate and scale analytical solutions and deploy them in production.
• Supporting data governance tasks: working with Privacy to ensure data usage and use cases follow GDPR, working with operational teams to measure and quantify big data value and impact.
• Supporting the definition and integration of data driven models and techniques into business and commercial systems to deliver value and improve customer experience.
• Leading the innovation agenda to promote experimentation, enable the development of prototypes, inspire innovation, attract and retain talent.
• Working with the Technology Lead and Data Engineers to define data migration and model deployment on the Big Data Platform, establish automated feeds and define best practices.
• Defining the data science roadmap, planning and execution according to business priorities. Main use cases: up-sell and cross-sell, customer retention and satisfaction, digital behavior, mobility, network quality, fraud, credit risk.
• Definition and adoption of new, cutting-edge tools, agile methods of working to create a more responsive, efficient and effective data science workflow and organization.
• Deploy H2o machine learning pipeline on wireless customer propensity (churner and buyer) prediction models.
• Micro segmentation to categorize and target best potential churner or buyer group utilizing PCA, Random Forest, GBM and Surrogate Tree technique.
• Build Isolation Forest model to quickly identify suspicious anomalies for fraud detection.
• Venue analytic to collect customer demographics information on special event, which will be provided for mobile store deployment