Profile Required

Exp : 6-8 years of relevant work experience in data science

Requirements:
You should have solid data-mining and analytical skills, including experience dealing with a large amount of data and good understanding of latest data-mining algorithms and will be working in one or more of the following: Python, R, SQL and PySpark.
You’ll be working with the large operational data-sets and complex business problems.
Setting up prediction models and building up algorithms to automate operational tasks shall form the major responsibilities.
Most of the problems are unexplored in this system and thus you’ll get a chance to work on innovative and challenging problems with unique data sets. Your strategies shall be executed on a real time basis and would tie up closely with operational efficiency.
You should be a Data enthusiast with a practice of approaching problems in a mathematical manner.
We would prefer candidates who can code their algorithms and can simulate their validity.
You will also work with cross-functional team members to identify and prioritize actionable, high-impact insights across a variety of core business areas.
Conduct feature engineering for the purpose of credit scoring by massive data mining.
Select features and train credit scoring models on large-scaled distributed data processing platform.
Analyze massive behavioral data and third party data and help implement anti-fraud, user profiling and value tracking frameworks.
Minimum Bachelor’s Degree in Computer Science/Statistics or related fields.
Deep understanding on feature selection and modelling. Familiar with the theories behind common models (logistic regression, random forest, boosting trees, neural network etc.), and experienced in fine-tuning.
Solid foundation in maths and programming.
Proficient in Python and related data processing libraries such as pandas and numpy.
Diligent and reliable, with excellent analytical skills, communication skills, and teamwork.

Other skills:
• Should have Strong ML model experience in complex data and positive mindset to achieve business objectives in smarter way.
• You should have a strong background in mathematics/statistics.
• Technical developer should have design/architect and development skills.
• Preferred having agile scrum methodologies or worked on Agile projects.
• Should have good experience in documenting business processes, workflows and requirements.
• Close collaboration with various domains within organization
• Collaborative Conceptualization
• Strong clear communication skills.
• Familiar with Apache Spark.
• Won award in machine learning related competitions/academic research experience on machine learning.