Psychographic Segmentation and Predictive Analytics for Superannuation
Janus Analytics was engaged by an industry super fund to build and implement predictive modeling and a segmentation system. The fund recognized that its broad membership base had varying needs, but lacked the foundations for creating a more targeted approach to communication and engagement. In 2014, the fund approached Janus Analytics with a vision to develop segment profiles of members, using their existing database. The results of the segmentation were to be used by the fund to establish tailored messaging for both existing and new members.
Janus Analytics worked with the fund to analyse available data from the fund’s database based on segmentation objectives that revolved around member engagement. Janus Analytics further combined this analysis with insights leveraged from previous research around behavioural segmentation. In turn, engagement segments were identified and defined to assist in building conversations with these potential segments.
To complement this approach to segmentation, Janus worked with the fund to gain a detailed understanding of its members and prospects. Janus further developed the segmentation model for existing members to include consideration for demographic, socio-cultural and behaviour factors. The overarching objective for the fund was to enable tailored communications and end-to-end CRM offerings specific to a range of customer profiles.
Janus Analytics developed a segmentation model solution which incorporated life stage, wealth and engagement dimensions. The segmentation model served as the strategic basis for matching the needs of various members and potential members with more targeted communications and service offerings. The model included highly developed visual representations of key ‘personas’ within the segments, including motivations and life perspective. The model also delivered key predictive analytic scores at an individual level that facilitated highly accurate targeting of the best prospects for various cross-sell activities and switching risk retention strategies. Subsequent testing of the analytics confirmed remarkably accurate predictions, often within a 5% accuracy tolerance. For example, the organisation was able to effectively target members for insurance and advice conversion with great success. The organisation was also able to stem the increasing tide of self-managed super fund (SMSF) departures with customised retention campaigns.Back Home