Applied Machine Learning Scientist II; Retail

Position: Applied Machine Learning Scientist II (Retail) 4031
*
* Work Location:

** Toronto, Ontario, Canada
*
* Hours:

** 37.5
** Line of Business:
** Analytics, Insights, & Artificial Intelligence
** Pay Details:**$110600 - $154000 CADThe pay details posted reflect a temporary market premium specific to this role that is reassessed annually.

TD is committed to providing fair and equitable compensation opportunities to all colleagues. Growth opportunities and skill development are defining features of the colleague experience  compensation policies and practices have been designed to allow colleagues to progress through the salary range over time as they progress in their role. The base pay actually offered may vary based upon the candidate's skills and experience, job-related knowledge, geographic location, and other specific business and organizational needs.

As a candidate, you are encouraged to ask compensation related questions and have an open dialogue with your recruiter who can provide you more specific details for this role.
*
* Job Description:

**** Department

Description:

** Retail Model Development (RMD) is part of the Model Development group and responsible for the development of credit risk models (e.g. capital models such as PD/LGD/EAD or scorecard models such as application or behavioral score) on retail portfolios. RMD also plays an essential role during the full model lifecycle beyond development, supporting model validation, monitoring, implementation and compliance reviews, to make sure all the models satisfy business needs and at the same time comply with regulatory requirements.*
* ***
* Job Description:

** The successful candidate will be a member of the Retail Model Development (RMD) team responsible for the development of retail scorecard models that are used in TD's adjudication, account management or collection strategies/policies.

Detailed and key accountability includes (but not limited to):
* Discuss business needs with LoB partners and scope the model target/use case before development.
* Extract data from data warehouses and analyze the data quality of existing features from large data sets and apply appropriate data preparations such as missing imputation or outlier treatment. Ensure business insights are incorporated in the data manipulation stage. Maintain exceptional code quality tracing all data operations.
* Engineer additional features if needed, such as transactional data aggregation or trends reflecting feature changes over time.
* Use Machine Learning (ML) algorithms, such as XGBoost or Neural Network, to fit the scorecard models. Analyze cross validation results to improve the hyperparameter tuning, or model performance metrics to propose additional feature engineering or segmentation to improve fitting on specific risk dimensions.
* Analyze feature contribution of the ML models with attribution tools such as SHAP or LIME, to make sure insights from data mining are still intuitive to LoB partners.
* Document clearly the modeling steps and decisions, as well as all performance and bias/fairness test results, for validation and compliance review. Support additional analysis requests from validation or compliance partners during those reviews.
* Collaborate with the model implementation team to move the model from development to production, and with the monitoring team to analyze any changes in model performance or feature attribution over time.
* Explore next gen data or methodology for retail credit scorecards, such as open banking data or Gen AI modeling framework.
* Contribute to codebase pipeline enhancement related to data preparations and model development routines*
* ***
* Job Requirements:

**** Minimum required experience
*** 3+ years of relevant experience in quantitative credit risk modeling and analytics.
* Advanced degree in one or more of the Science, Technology, Engineering, and Mathematics (STEM) areas such as Mathematics, Physics, Engineering or Computer Science.
* Hands-on expertise on large data manipulation in SAS, SQL, python or pyspark.
* Demonstrated ability to synthesize clear insights from data
* Experience working with Git Hub
* Advanced python programming skills in Databricks including classes, modules packaging and…