NMSI - Exhibiting expertise, understanding membership and increasing donations for the NMSI

Download Case Study

Background

NMSI is the group name for the Science Museum in London, the Railway Museum in York and the Media Museum in Bradford.

The NMSI membership scheme, SCIM Plus, is relatively new and offers free entry to paid exhibitions and exclusive previews, in addition to discounts in the shops and cafes. NMSI had not previously undertaken any analysis of their members or visitors, despite the Science Museum in particular facing stiff competition from nearby museums and other London attractions.

Challenge

NMSI wanted to understand how to increase the retention rate of members within SCIM Plus. In addition, they also wanted to identify which members could be more involved with an individual-giving programme.

Both of these objectives could be achieved through a greater appreciation of the profile of their members, patrons and visitors including where they lived and which museum they visited most often.

Solution

Our recommended solution was to conduct a range of analysis and create models which would enable them to:

Profile the member base
Understand where members lived in relation to their closest museum
Create member segments
Predict lapse of membership
Predict the likelihood to donate
Identify potential patrons

The initial priority was to clean and enhance all of the data so that it was mailable and fully compliant.

Following from this, a full socio-demographic profile was created for each of the museums and across the different member types.

Then a geographical distribution of the members and visitors was established to identify the member and patron penetration in the locale of each of the museums. To complement this, a bespoke segmentation was built to identify different member segments using a mixture of key variables including age, gender and length of membership.

The next stage was to create a predictive model using data such as type of membership, distance from museum and Cameo group. This enabled each member to be scored which reflected their likelihood to lapse.

Finally, the combination of profiling and geo-location based insight helped to highlight those individuals most likely to become patrons.

Results

A much greater understanding of all prospects and visitors was established.

The successful creation of the models means that each member is scored and segmented and now receives more relevant and personalised communications. This has helped to ensure they are fully engaged within the membership programme. The results of which have reduced their attrition rates and driven increased donations.