Description: The newer predictive modeling tools are powerful but they work best when supported by a lot of computing power. Parallel processing is very powerful but often very difficult to implement. Dihui and Richard take us through the maze of options with H2O, SparkNet/MLib and Mahout. Which do you use for a generalized linear model (GLM), and which is better for high-volume data manipulation?

Description: Richard Xu and Dihui Lai continue this lesson with “Data Clustering and its Application in Insurance,” where they teach us a procedure for clustering and useful measures for proximity; and then they apply the theory to an application involving the risks associated with foreign travel. They conclude with an observation that can help us better underst and client behavior and market segmentation.

Description: This actually is a copy of an appendix of a research paper sponsored by the SOA Committee on Finance Research. You can read the entire research paper: “Lapse Modeling for the Post-Level Period—a Practical Application of Predictive Modeling” at the SOA site https://www.soa.org/Research/Research-Projects/Finance-Investment/lapse-2015-modeling-post-level/#sthash.W9lERSls.dpbs, but you can read this valuable appendix copied here in this issue to see how to build a PM step-by-step using your data and the R programming language. We thank Richard Xu, Dihui Lai, Minyu Cao, Scott Rushing, and Tim Rozar for their excellent paper and the Society of Actuaries, for the permission to reprint this portion of the paper.

Description: In this article, we will overview some popular tree-based models and understand how such models may be applied to the insurance industry.

Description: Unstructured data is often synonymous with Big Data; and the term is used and misused a lot. Richard Xu and his colleague, Dihui Lai, dispel some of the confusion about Big Data in their article “Big Data In Life Insurance—Does It Exist? If So, How Should We Handle It?” They address some of the ways to deal with the mounting challenges of capacity and speed as data scales up rapidly in size. Hadoop was once just the name of a toy elephant; but there is nothing toy-like about how it has been employed to handle very large datasets. Five exabytes supposedly represents all the words ever spoken by human beings; but according to IBM, the new SKA telescope initiative will generate over an exabyte of data every day.1 How will we cope with big data? Read Richard and Dihui’s article for some hints.

Description: In this article, we are going to discuss the AR model by making connections to time-dependent ordinary differential equations.

Description: Spark offers a way to get some dramatic speed and scalability advantages over the Map-reduce methodology whenever you are doing iterative data processing and particularly when you want interactive data analysis capability. Find out why “lazy execution” can be a desirable characteristic when dealing with big data.