Our latest blog series focuses on Quest’s pricing capabilities. We discuss how behavioural insight improves expected loss valuations, the significance of influential factors, how premiums are forecast based on big data and what it means for the insurance industry.
We have previously discussed the impact of predictive pricing on the roles of Brokers, Actuaries, (Re)Insurers and Capital. Specifically, how they can differentiate to become more competitive within the market. The changes in business practice that are possible from a data-led benchmark can greatly affect business performance.
Predictive pricing provides a quick, holistic assessment of risk which informs Underwriters of an account’s expected loss. It is a far stronger benchmark for Underwriters when compared to traditional pricing techniques. This is due to the ability to capitalise on vast datasets to calculate a valuation based on both static and behavioural factors. The use of a more accurate benchmark drives consistency, accuracy, and transparency throughout the underwriting process.
Automating the interpretation of such large datasets and modelling based on behavioural insight makes this tool a significant progression of industry practice. Underwriters can make far more informed decisions around writing risk, allowing them to assess the impact of each account on their loss ratio. This means they can review more accounts in more detail over time, improving productivity. Reclaimed time can be used to build Client relationships and therefore attract new business. The compound effect of writing better risk at account level ultimately impacts the portfolio, improving overall business performance.
Portfolio management is a further use of this metric, as Underwriting Managers could enforce consistency throughout their teams by providing them with a minimum threshold to adhere to.
The ability to leverage vast datasets to create a more accurate method of predicting loss has a slew of benefits that influences the entire insurance value chain. Whilst more consistent and informed underwriting will uplift the profitability of the industry, the visibility of contributing factors adds-value through understanding. (Re)Insurance Brokers, MGA’s and Underwriters can utilise vessel score to advise on account investment through data-led consultation.
Traditional pricing models can be very rigid as they can only be updated once a year. The right machine learning processes allow models to be updated more regularly, allowing for a more competitive pricing structure over time.
Influential factors build on a transparent view of risk, allowing any user to see which factors are contributing to the expected loss value of an account. Concirrus’ models use over 250 variables when assessing risk score, including casualty data. Consultation can therefore expand into a multitude of best practice reviews including safety, time in port, vessel type, monthly distance, etc. This can be done ad-hoc, allowing for cadence in monitoring as well as measuring Key Performance Indicators (KPI’s) over time.
With such methods of assessment in place, modern technology will be able to satisfy the needs of the market in the current landscape. This will only develop further, with this new series of posts demonstrating how behaviour differentiates vessel value, the significance of influential factors, and the ability to not just derive an expected loss, but forecast premiums based on big data.
For more on how business capabilities can change due to innovation in pricing, read the white paper or get in touch.