O'Reilly on Data

DECEMBER 12, 2019

Model debugging is an emergent discipline focused on finding and fixing problems in ML systems. In addition to newer innovations, the practice borrows from model risk management, traditional model diagnostics, and software testing. Residual analysis is another well-known family of model debugging techniques.

Machine Learning 191

Machine Learning Modeling Testing Risk Management 191

BizAcuity

APRIL 1, 2023

Anti-Money Laundering (AML) is increasingly becoming a crucial branch of risk management and fraud prevention. The algorithms can detect anomalies in the transactional data and helps to identify high-risk customers and transactions that may be linked to money laundering activities.

Machine Learning 52

Machine Learning Predictive Analytics Predictive Modeling Risk 52

O'Reilly on Data

MAY 18, 2020

All predictive models are wrong at times?—just As the renowned statistician George Box once quipped , “All models are wrong, but some are useful.” Broadly speaking, materiality is the product of the impact of a model error times the probability of that error occuring. just hopefully less so than humans.

Risk 359

Risk Modeling Data Processing Software 359

BizAcuity

JANUARY 18, 2023

Anti-Money Laundering (AML) is increasingly becoming a crucial branch of risk management and fraud prevention. The algorithms can detect anomalies in the transactional data and helps to identify high-risk customers and transactions that may be linked to money laundering activities. These include-. REFERENCES. [1]

Machine Learning 52

Machine Learning Predictive Analytics Predictive Modeling Risk 52

DataRobot Blog

JULY 22, 2022

That requires a good model governance framework. At many organizations, the current framework focuses on the validation and testing of new models, but risk managers and regulators are coming to realize that what happens after model deployment is at least as important. Legacy Models. Future Models.

Modeling 105

Modeling Risk Management Testing Risk 105

Cloudera

SEPTEMBER 7, 2023

But these measures alone may not be sufficient to protect proprietary information. Even when backed by robust security measures, an external AI service is a tempting, outsized target for potential security breaches: each integration point, data transfer, or externally exposed API becomes a target for malicious actors.

Insurance 78

Insurance Risk Data-driven Finance 78

Insight

FEBRUARY 19, 2020

I held out 20% of this as a test set and used the remainder for training and validation. Feature Selection and Engineering Most of the inputs to my model were taken either as is from the data source, or with minimal processing. Scatterplot of the predicted ROI vs. the true ROI for the hold-out test set. A New Hope ).

Risk 67

Risk ROI Modeling Metrics 67