Using Classification Techniques to Accelerate Client Discovery: A Case Study for Wealth Management Services

The retail side of the finance industry is currently experiencing a deep transformation associated to the rise of automation technologies. Wealth management services, which are traditionally associated to the retail distribution of financial investment products, are of course impacted. The retail distribution of financial instruments is currently normalized for regulatory purposes. It yet remains costly. Documented examples of the use of automation technologies to improve its performance (outside of the classical example of robo-advisors) remain however sparse. This work shows how machine learning techniques under the form of classification algorithms can be of use to automate some activities (i.e. client expectations analysis) associated to one of the core steps behind the distribution of financial products, namely client discovery. Once calibrated to a proprietary data-set owned by one of the leading French independent software vendors specialized in the wealth management segment, standard classification algorithms (such as random forests or support vector machines) are able to accurately predict the majority of households financial expectations (R.O.C either above 80% or 90%) when fed with standard wealth information available in most of the database of financial products distributors. This study thus shows that classifications tools could be easily embedded in the digital journey of distributors to improve the access to financial expertise and accelerate the sales of financial products.