At Globe, our goal is to create a wonderful world for our people, business, and nation. By uniting people of passion who believe they can make a difference, we are confident that we can achieve this goal.
Job Description
The Model Development Lead is responsible for managing analytics projects from development to operationalization, performing analysis and predictive modelling and helping drive the change management process. Responsible for ensuring machine learning jobs are running in production and provide integration to existing and new systems.DUTIES AND RESPONSBILITIES:
Model Development Lead is responsible in handling modeling projects including but not limited to the following :
1. Data Management and Exploration
● Extraction, exploration and manipulation of large and complex data sets
● Designing and derivation of transformed variables for predictive modeling/advanced analytics
● Develop big data framework combining telco data with various external sources of data (digital, social, etc) to get a 360-degree view of the customer
● Help internal stakeholders in understanding, interpreting and analyzing massive data sets
2. Data Analytics and Modeling
● Understand and translate business problems into data science projects.
● Perform data modeling and create sophisticated analytics models. Implement and test data modeling designs. Use advanced math and statistics expertise using massive (beyond 500GB) data. Use modern data analytical techniques working with information retrieval, machine learning, matrix and graph algorithms, unsupervised clustering & data mining to solve business problems
● Track model accuracy and effectiveness
● Identify model fine-tuning needs; Measure ROI from models developed
3. Campaign Expertise
● Translate model into results. Draws out and communicates useful insights, actionable interpretations, alternative approaches and solutions.
● Identify opportunities for the application of customer analytics techniques for the business, particularly for credit scoring.
● Use learnings from models to prioritize and sequence initiatives; Collaborate with business sponsors and different stakeholders to operationalize analytic findings.
4.Knowledge Transfer and Collaboration
● Support internal stakeholders in use of data and various analytical tools to generate and communicate insights
● Provides training, demonstration, documentation and other support to drive the change management process and expand the use of analytics throughout the organization
● Support the drive for change management process to ensure the analytical developments are adopted by relevant internal teams.
● Develop relationships with external data and analytics partners and interact as needed.
● Keep updated with new data science techniques and be extremely knowledgeable of industry standards and trends.
REQUIREMENTS:
Minimum of three (3) years’ experience in customer analytics domain and/or credit risk assessment and financial services, covering most of the following: data mining, predictive modeling, machine learning, statistical modeling and analysis, large scale data acquisition, transformation, and cleaning, both structured and unstructured data
Proven track record of leading and collaborating on advanced analytics strategic initiatives; Proven track record of operationalization of analytic models in collaboration with marketing/risk and IT teams
Worked with large, unfiltered data sets or data science research
Has Knowledge of both structured and unstructured data
Must possess core competencies, deep understanding and relevant experience in a. Scripting or programming experience: familiarity in programming languages with relational databases (e.g. Python, Java, Ruby, Clojure, Matlab, Pig, SQL)
Statistical Analysis: advanced usage of off-the-shelf tools such as R, SAS, SPSS, Sagemaker,Weka and other analytical tools or software
Big Data: Experience with Big data tools such as Snowflake, HDFS, Cassandra, Storm
Database knowledge: skilled in structured database
Familiar with most of the following disciplines
Conceptual modeling: to be able to share and articulate modeling;
Predictive modeling: most of the big data problems are towards being able to predict future outcomes
Hypothesis testing: being able to develop hypothesis and test them with careful experiments
Natural Language Processing: the interactions between computer and humans
Machine learning: using computers to improve as well as develop algorithms
Statistical analysis: to understand and work around possible limitations in models
Bachelor's Degree in quantitative discipline such as Statistics, mathematics, Operations Research, Engineering, Computer Science, Econometrics or Information Science such as Business Analytics or Informatics
Make Your Passion Part of Your Profession. Attracting the best and brightest Talents is pivotal to our success. If you are ready to share our purpose of Creating a Globe of Good, explore opportunities with us.
