Predicting High-Risk Clients

Our focus is finding a way to accurately predict high-risk clients based on their likelihood of claims and damages within a year.

Handling Imbalanced Datasets

Having an imbalanced dataset is one of the critical problems of machine learning algorithms.

Diversification Reflex

Risk selection is not about blind diversification, it is about right kind of diversification.

Three Pillars of Risk Analysis

At Urbanstat, our philosophy of risk analysis is all-embracing and rests on three complementary pillars.

Thoughts on DWIC 2017

As February turns to March, we were in Dubai to talk about latest developments in the insurance industry.

January 2016 to January 2017

From January 2016 to January 2017 UrbanStat has been taking major steps to expand into the US market.

Importance of External Datasets in Claim Prediction

We have seen remarkable differences in our models when we used external datasets.

A Short Analysis of Storm Grayson

In the first week of January 2018, East Coast battled with a colossal bomb cyclone that affected more than 100 million people.

We join AAIS as Associate Partner

We are excited to join AAIS as an associate partner and to provide opportunities for its members to improve their underwriting capabilities.

Ensembling Multiple Machine Learning Models

Model ensembling is one of the most used methods in order to improve machine learning performances one step further.

The Hardest Obstacle of Insurance Analytics: Legacy Systems

“Their tech is great, but what can we do with it?” Statements like these are commonplace among boardrooms discussing how an InsurTech vendor solution is viewed within the walls of a carrier.

The Most Crucial Step in Predictive Modeling

At UrbanStat, before we start modeling, we review the initial data extensively. We believe preprocessing is one of the most important steps of machine learning modeling.