Description: Often actuarial practitioners are faced with working with data that is less than ideal. The data may be observed with gaps in it, a model may suggest variables that are observed at different frequencies, and sometimes predictive analytic results are very fragile to the inclusion or omission of just a few observations in the sample. Data, particularly big data, are often "messy" and something must be done about it. What is the actuary to do about these very practical matters? These types of questions are what this presentation is intended to address. Concerns on missing data, outliers, nonlinearity, mixed-frequency, cross-correlations are illustrated using real datasets in the Asia-Pacific countries. Some possible solutions to the messy data problems will be discussed.

Description: Often actuarial practitioners are faced with working with data that is less than ideal. The data may be observed with gaps in it, a model may suggest variables that are observed at different frequencies, and sometimes predictive analytic results are very fragile to the inclusion or omission of just a few observations in the sample. Data, particularly big data, are often "messy" and something must be done about it. What is the actuary to do about these very practical matters? These types of questions are what this presentation is intended to address. Concerns on missing data, outliers, nonlinearity, mixed-frequency, cross-correlations are illustrated using real datasets in the Asia-Pacific countries. Some possible solutions to the messy data problems will be discussed.

Description: You’ve built or updated a predictive model. Is it any good? How can you interpret and understand its predictions? How does it compare to alternative models? This session will look at traditional and non-traditional ways of validating predictive models, with examples from case studies.

Description: Highlights of two 2018 health events organized by the Colombian Association of Actuaries and sponsored by the Colombian Government. Seminar on Risk Adjustment and Predictive Modeling in Health. Seminar on Risk Management for the Health Insurers

Description: Health claims are not normally distributed. Claims Forecasting can be improved by understanding the entire distribution of plausible values of future claims, for example knowing there is an 80% chance future claims are between $340 and $375 PMPM. Confidence intervals around our estimates allow us to understand for each range around the best estimate (for example +/- 1%) what is the probability that future claims will fall in that range. Quantile Regression is a mathematical technique where you can estimate any percentile of the claims distribution you are looking for as a function of demographics, diagnosis indicators, prior cost variables, or other significant predictors. You can see which coefficients are important at different parts of the distribution. Individual and group distributions can be constructed. There are numerous applications in pricing and underwriting, stop loss, provider profiling, ACO target setting, allocation of group risk charges based on volatility, discounting strategy, and experience analysis.

Description: Uncertainty of a predictive model is a fact of life that many insurers could be overlooking at their peril without a framework for assessing it. The article provides a framework to understand the prediction uncertainty, which can be critical for the insurance operations using predictive models. Coin toss example explains model uncertainty and randomness inherent in making predictions to the number of heads expected. A mortality analysis case study illustrates how the Bayesian methodology can be used to develop the prediction uncertainty. In particular, the article shows that the Bayesian framework is a way to combine historical data and actuarial judgment, and directly address the model uncertainty through its posterior distribution.

Description: Discussion of machine learning applications currently being used to augment traditional actuarial modeling in the life insurance industry. This includes data science techniques for: Quantifying and explaining differences between model versions or reporting periods Building proxy models for actuarial model output using machine learning One-class classification for data integrity checks Applications of unsupervised learning (e.g., clustering and principal components analysis) to reduce model run time

Description: Deep learning neural network applied to experience analysis for post-level term lapse and mortality.

Description: We compare two predictive analytics methods - GLM and GBM in terms of predictiveness vs. interpretability.