Neova Sigorta transforms insurance pricing with SAS and AI

Turkish insurer Neova Sigorta has launched an initiative to offer better auto insurance premium prices to up to 95% of its customers. This development is projected to save Neova Sigorta’s customers money – and decrease overhead costs for the insurer.

The  first of its kind in the Turkish market, the service will use advanced machine learning (ML) to optimise how it prices auto insurance. Neova Sigorta selected SAS Dynamic Actuarial Modeling, a pricing solution with AI-based premium modelling for general and life insurers, as its platform of choice for its transformation. Software and consultancy firm Sade Software & Consultancy (Sade Yazılım), an SAS partner, will be the initiative’s integrator.

The deployment, expected to last between six and eight months, will help Neova Sigorta offer more appealing prices to new and existing customers. It is also expected to significantly increase market share in new regions and bolster renewal rates in established regions. Similar collaborations between SAS and SADE have demonstrated that the right pricing policy can increase sales up to 15% and decrease the insurer’s combined ratio by 10%.

“In our business, we always prioritise customer comfort and satisfaction above all else, and we know that affordable premiums are one of the main factors that contribute to customer happiness and retention,” said Neslihan Neciboğlu, Neova Sigorta CEO and board member. 

“We’re thrilled to work with SAS and SADE on this project that will make our customers even more satisfied with the Neova brand.

“We evaluated several platforms to implement this project. SAS Dynamic Actuarial Modeling was the most comprehensive platform, allowing us to train, deploy and automatically monitor the performance of high-accuracy machine learning models. We also appreciated that SAS’ solution capabilities can be extended to other critical functions such as next-best offer generation and insurance fraud detection, aiming to improve customer experience and reduce prices even further.”

“Since the establishment of SADE, our work in the insurance sector has been one of our focus areas, and we’ve implemented many projects for fraud detection, data quality and other use cases in the Turkish market,” said Deniz Çelik, SADE co-founder.

 “The machine learning-based pricing project with Neova Sigorta and SAS is of special importance to us, as it is one of the first and finest examples in the region.

“Neova Sigorta truly understands the importance of AI and ML, and the company’s knowledge and vision put them ahead of many players in the market and in the underwriting field.”

Auto insurance pricing has historically been based on generalised linear models (GLM). Although these models have good interpretability – performance that is predictable and easily explained – the accuracy of estimates tends to be limited, ultimately resulting in higher prices and lower sales, SAS said.

Limited sample sizes and risk assessment policies can significantly lower the quality of the data used to train GLMs through causing errors and introducing bias, for example.

Looking to modernise, Neova Sigorta will switch to ML algorithms to price its auto offerings instead. Unlike GLMs, ML algorithms do not make any assumptions about the properties of the data the models are using. These algorithms also consider more variables that define customer behaviour and are designed to extract more granular patterns in the data. ML algorithms can therefore produce much more accurate and realistic results.

“Fair, accurate and timely insurance policy pricing is a necessity for insurers in all markets,” said Stu Bradley, Senior VP of Risk, Fraud and Compliance Solutions, SAS.

“Consumers often look for more affordable insurance options amid inflation and other economic turbulence. If insurers can’t offer competitive pricing, they risk losing customers to the competition – and agents often follow when they can’t achieve their goals. This can severely damage an insurer in mere months.

“Switching to a modern, machine learning-based approach with real-time decisioning capabilities will greatly improve an insurer’s bottom line. As important, is built-in model governance. Making these decisions in a trustworthy and transparent way is critical to ensuring satisfied customers.”

“As insurers – and the financial services sector at large – invest in AI, they want to see quantifiable profitability and tangible benefits for customers,” added Rasim Eğri, GM, SAS Turkiye & Central Asia. 

“This use case demonstrates the abundant possibilities that await as industry moves into the AI-powered future. Neova Sigorta is blazing a trail for insurance innovation.”