Determining if a customer has had a positive cinema experience can be readily obtained from survey data. However understanding the drivers of such an experience requires a deeper analysis. Is there a single driver or a multitude of them, that act in partnership, to drive the customer experience? Do these factors vary across different cinemas or customer types? Are there external factors, such as weather conditions, that affect a customer experience or worse, create spurious correlations in the data?
Using machine learning with survey, transactional and geographical data-sets we were able to build nonlinear models to predict a customer’s experience. From here we then applied novel data science techniques to identify and rank how influential these factors, individuals or in combinations, are on the customer experience.
Going further we investigated whether the key drivers of a positive experience could vary across different customer segments and regional areas. Using unsupervised machine learning techniques we optimally clustered customers and geographic regions into segments. We were then able to derive the key drivers for each segment and compare and contrast how they differed from group-to-group. From this in-depth analysis we discovered that the drivers of the customer experience do not have a one size fits all answer.
key factors identified out of 60+ that drove a positive customer experience
new customer segments identified
forecasting accuracy of our models
55% more reliable bug identification
We identified errors in C and C++ programs faster and more accurately than the existing technology.Learn more
1000X faster cable network planning
We created a way to plan fibre round a town in seconds – more than a thousand times faster than the existing approach.Learn more
Mobile cells optimally placed
We placed mobile network infrastructure to maximise coverage whilst minimising equipment costs.Learn more
Mariflor Vega Carrasco
Thank you for contacting us, we will come back to you as soon as possible