Most recent
-
Factorization Machines for High Cardinality Features (Part 4 of 4)
This is the fourth in a 4-part series where Anders Larson and Shea Parkes discuss predictive analytics with high cardinality features. In the prior episodes we focused on approaches to handling individual high cardinality features, but these methods did not explicitly address feature interactions. Factorization Machines can responsibly estimate all pairwise interactions, even when multiple high cardinality features are included. With a healthy selection of high cardinality features, a well tuned Factorization Machine can produce results that are more accurate than any other learning algorithm. -
The Hashing Trick for High Cardinality Features (Part 3 of 4)
This is the third in a 4-part series where Anders Larson and Shea Parkes discuss predictive analytics with high cardinality features. In this episode they focus on feature engineering via the hashing trick. The hashing trick is most applicable for extremely high cardinality, and at first glance can seem almost ridiculous. In a lot of ways, it is the same as bucketing values at random. But there are times that it is more valuable to include randomly engineered buckets than to exclude the original high cardinality feature entirely. -
Abandon the Spreadsheet and Go Digital
Lin Fangcheng argues that it is easy to digitalize by setting up new departments, but the real battle is to digitalize the incumbent departments that are predominantly spreadsheet-users. In order to reap the full potential of digitalization, we must abandon the spreadsheet and go digital. He discusses the reasons why the spreadsheet, hindered by its inherent design, has become a bottleneck for higher efficiency, and how to adopt low-code digital technology in a “together” mode. He further demonstrates that digitalization lays a solid foundation for artificial intelligence. -
Predictive Analytics Hack-a-Thon 2022
Describes the Predictive Analytics Hack-a-Thon held in 2022 and its outcomes. -
Y-aware Feature Engineering with High Cardinality Features (Part 2 of 4)
This is the second in a 4-part series where Anders Larson and Shea Parkes discuss predictive analytics with high cardinality features. In this episode they focus on y-aware feature engineering. Y-aware feature engineering is all about carefully bleeding information from your training response back into your engineered features without grossly misrepresenting your ability to generalize to new data. -
Introducing Predictive Analytics with High Cardinality Features (Part 1 of 4)
This is the first in a 4-part series where Anders Larson and Shea Parkes discuss predictive analytics with high cardinality features. In this episode they focus on introducing what high cardinality features are, why you might want to work with them and some of the basic approaches to including them in predictive models. -
An Exploration of the Quantum Actuary
Quantum theory is one of the significant concept in modern physics. Many phenomena in nature and society also show the characteristics of "quantization", of course including the insurance market. Probability is the cornerstone in the actuarial calculation while the quantum mechanics could give different perspectives on the probability. The paper proposes a new approach to explore the quantum application to the insurance market by solving the partial differential equation of the Schrödinger equation with some simple Hamiltonian such as infinite square potential well, potential barrier penetration and harmonic oscillator which may be helpful for the development of quantum actuarial. -
The Tests Never End: An Overview of Software Testing Methods for Actuaries – Part 3 of 3
This is the third and final installment of a 3-part series where Joe Alaimo and Andy Rallis discuss the different types of software testing, what they are, how they are performed and ways that they apply to the software development that actuaries are involved in. -
Speculative Fiction Contest: New Name and Expanded Ways to Enter and Win
An announcement about the new name of the Speculative Fiction Contest as well as some information about the contest's new categories for entry. -
Immunize Against Inflation Risk? Protecting an Insurance Portfolio Against Persistent Inflation
It is prudent to raise an alarm over the persistency of current inflation risk as part of a proactive risk management strategy. There is a chance that the current rise in inflation may subside as has happened numerous times during the past decades, but that does not preclude the need to build a robust portfolio that can withstand a more sustained and persistent inflation shock. I hereby present a framework to construct an optimal portfolio that protects investors against persistently higher inflation.
Welcome to our medium.
Dive into insightful content. Gain practical knowledge. Explore the latest research and key information for future use. Discover the Emerging Topics Community, an online forum that focuses on three main topic areas–Modeling, Predictive Analytics and Futurism, and Technology.