Machine Learning

II. Probabilistic Programming: Survival Analysis

Introduction This is a second article in the series of Probabilistic Programming for Actuarial Science. The first article introduced the Bayesian approach to inferring risk rates and predicting future claims in an actuarial context and built a practical model in Greta, a probabilistic programming language, to conduct the analysis. In a beta binomial model, a …

II. Probabilistic Programming: Survival Analysis Read More »

I. Probabilistic Programming for Actuarial Science

Introduction A core task of actuarial analysis is estimation of risk rates for insured events. This includes analyses such as estimating mortality rates, lapse rates, incidence rates, termination rates and so on. In addition to determining best estimates for risk rates, understanding the uncertainty around the best estimates is a critical component of the overall …

I. Probabilistic Programming for Actuarial Science Read More »

Tracking Presidential Polls: A New Approach

Final Review: A summary of the final results can be found here. Original article: 7/22/2016:  Being in the height of the presidential election season, there is intense interest as to who is likely to win the November elections.  The standard approach in the press has been to commission a poll, report the results and compare …

Tracking Presidential Polls: A New Approach Read More »

Turing Award goes to Bayesian Network Specialist

The Turing Award, which is the computer science equivalent of the Nobel Prize, was awarded to Judea Pearl.  Pearl was honored for his contributions to artificial intelligence.  He championed a probabilistic way of creating smart computer systems rather than building a set of rules.  These systems are encapsulated in Bayesian Networks. Bayesian analysis forms a …

Turing Award goes to Bayesian Network Specialist Read More »