Home Math for a better future

Chi siamo La nostra identità

Piattaforme I prodotti di Moxoff

Soluzioni La matematica per evolvere

Casi studio Esempi di storie di successo

Education La formazione su misura

Contattaci Il filo diretto con gli specialisti

Home

Chi siamo

Piattaforme

Soluzioni

Casi studio

Education

Contattaci

Magazine Unisciti a noi

Case study

Telco & Utilities

z = −1 + i nα = θ + 2πk f(x) = 3x − 2 z = r (cosθ + isinθ) (f(−x) = f(x), ∀ x ∈ D) ax + by + cz + d = 0 −x + 2y + z + t = −1 2x + 2y + z + 4t = 0 C = {z = x + iy x, y ∈ IR}

Telco & Utilities

Analytics to understand and prevent churn

Bluenergy is a utility company operating in the gas and power supply market, with both business and residential customers. In recent years the number of terminations due to a change of trader is increasing and it is becoming more and more important to act proactively and in advance to contain this phenomenon. Our collaboration has resulted in tools to support churn analysis and prevention.

z = −1 + i nα = θ + 2πk f(x) = 3x − 2 z = r (cosθ + isinθ) (f(−x) = f(x), ∀ x ∈ D) ax + by + cz + d = 0 −x + 2y + z + t = −1 2x + 2y + z + 4t = 0 C = {z = x + iy x, y ∈ IR}

Over the years, our client has tried to investigate the causes of churn through one-off analyses, without making use of all the available databases. These analyses were not able to capture the complexity of the phenomena underlying churn, which are constantly evolving and involve a heterogeneous customer base. It also implemented retention and loyalty campaigns without measuring their effectiveness or targeting the customers with the highest churn risk.
Moxoff supported Bluenergy in the development of a series of analyses and in the definition of some customized KPIs that allowed for the analysis and monitoring of the multiple factors that have an impact on churn in order to plan effective retention actions.

Data enhancement

All customer data sources are used in the analysis

Multiple databases

Data from different sources are put into relation and analysed in a comprehensive overview

Actionable and robust insights

Retention actions can be planned on customers with higher churn risk

Find more on this case study

Deepening case study

Survival analysis to prevent churn

The work started with importing, reading and cleaning customer data and continued with the correlation analysis of data from different sources and contexts. After these steps, we developed correlation analyses between static customer characteristics and churn on one hand , and we dynamically quantified the effect of specific events on churn on the other. To do this, we applied survival analysis techniques, statistical tests, ad hoc dynamic analyses and defined performance KPIs.

Read another case study from the same industry

Focus