CVM Modeling Principle Professional

Job Summary

• Build outstanding, robust, working analytical solutions makes use of relevant Teradata based customer database, large analytical table and offer data (i.e. historical behavior, offer attributes) to identify the best customer and offer instance combinations in line with business objectives.
• Design, develop and maintain algorithms to extract relevant information from big amounts of data, scalable software systems and algorithms to clean, standardize, and analyze raw data.
• Develop and deliver model’s outcome and performance reporting, critical for tracking and managing the business, including weekly, monthly, and quarterly operational metric reports.
• Drive the implementation of the analytical strategy and work with functional business leaders to build scalable processes and metrics.
• Explanation and documentation of analytical model’s techniques and results.
• Identify new datasets to be captured to enrich the Large Analytical Table(s).
• Dig in and become an expert in our datasets, provide data insights, drive key improvement initiatives and work with other teams to integrate results into working products..
• Write clean, scalable and fast performing code according to guidelines and quality standards (solid principles, code readability, pattern use) and review other developers’ code.
• Pursue the generation of common components and best practices, fostering the reuse of technology and knowledge across software products, specifically in the data-mining domain.
• Participate in “make” vs. “buy” decisions from a technical point of view concerning technology.
• Simple and convincing communication, especially around the analytical concepts and solutions.
• Participate in and/or lead the technical decisions impacting on the product software being developed in order to assure that requirements are met and differential technology is created while balancing delivery constraints.
• Visualize and tell stories with data, take decision based on this data and present clear results.
• Interact and understand technical subjects/emerging technologies and their relevance to the marketplace.
• Demonstrated track record of prototyping and launching industry leading data-driven products.

Skills

• Extensive experience and hands-on of data management, implementation of machine learning algorithms and various statistical modelling techniques and deep learning approaches including: Support vector machines, Bootstrap aggregating / bagging, Cluster analysis, Cascading classifiers, Decision trees, Time series analysis & time series forecasting, Boosting, Factor analysis, Structural equation modelling, Item response theory, Markov chains, Voronoi diagrams, Neural networks, Genetic algorithms, Data visualization, Bayesian modelling, Multivariate regression, Logistic regression, etc.
• Good understanding of the science behind machine learning algorithms (supervised and unsupervised algorithms), statistical and optimization techniques.
• Ability to attach complex business questions with data and curiosity to dive deep, identifying the root cause and “so what” rather than just the trends.
• Thrive in an environment that is tasked with providing data-driven decision support and business intelligence that is timely, accurate and actionable.
• Eeffective prioritize projects, manage multiple competing priorities simultaneously and drive projects to completion under tight deadlines.
• Experience in data mining using databases in a business environment with large-scale, complex datasets.
• Effectively communicate with both business and technical teams.
• Think big, understand business strategy, provide consultative business analysis, and leverage technical skills to create insightful, effective BI solutions.
• Hands on experience in SQL, PL/SQL, Excel, Linux and OLAP, SAS, R and/or Python (data extraction, manipulation, data insights).
• Experience with data presentation and visualization software (Tableau, JasperSoft, QlikView, MicroStrategy, Business Objects) and able to translate complex insights in a story telling dashboard.
• Good understanding of Hadoop Ecosystem components, Hadoop MapReduce framework, streaming processing frameworks.
• Knowledge of Hadoop-based analytical tools (Mahout, Hive, Pig. RHadoop, MOA, Jabatus, Alpine, etc.)
• Proficiency in query languages like Hive and NoSQL databases like HBase is a plus.
• PHD is prefered.

Education

quantitative discipline – Computer Science Engineering/ Applied Mathematics/ Statistics.