The Issuer Services & Global Insights group employs hundreds of economists and financial experts to provide critical intelligence to public corporations, and governments. We employ data science techniques to analyze financial transactions, macro factors, industry details and hundreds of unique data sets to “know the mind of the investor”. Our machine learning models have been wildly accurate, even through the unprecedented post-Covid economy. We are looking for an experienced Data Scientist to take our flagship prediction platform to the next level.
- Experience with Financial Services or a similarly complex domain with transactions and time series.
- Proficiency with Python for Data Science and Machine Learning.
What you will do:
- Work closely with product owners, other data scientists, developers, designers, financial experts, economists, and others across the company to solve challenging business problems with technical expertise, curiosity and creativity
- Establish necessary business and domain knowledge to correctly interpret data and results and propose experiments, projects and products
- Weave together data sets from our robust data lake and extract actionable insights to guide decisions and improve business outcomes
- Bring analytical rigor and statistical methods to the challenges of measuring data quality, product performance, anticipating and interpreting the behavior of market participants
- Communicate data-driven insights and recommendations to non-technical stakeholders
- Own and lead projects, design and implement experiments, write production-quality code
- Collaborate with Software Engineers and DevOps to automate workflows and apply scientific methods to solve business and engineering problems
Who you are:
- You enjoy learning new techniques and sharing your knowledge with others
- You can work independently but have great collaboration skills
- You have 5+ years of related work experience in data analysis and machine learning (such as logistic regression, random forest, gradient boosting, clustering, classification, deep learning) and understand their real-world advantages/drawbacks on large datasets
You can demonstrate experience with the following:
- Deployment and maintenance of machine learning solutions in production
- Applying advanced statistical techniques and concepts (hypothesis testing, Bayesian statistics, properties of distributions) and experience with applications.
- Python, SQL
- Presenting results, insights and recommendations to executives and non-technical audiences
- Working with version control, preferably git based
Other desirable experience:
- Developed and implemented prediction engine in production
- Developed and implemented experimentation pipeline
- Worked with micro-service architecture
- Worked with .Net, C#, AWS, GCP