Customer Retention

The central purpose of managing customer relationships is for the enterprise to focus on increasing the overall value of its customer base and customer retention is critical to its success.”

Peppers and Rogers

 

Customer churn (aka Customer Retention) occurs when customers or subscribers stop doing business with a company or service, also known as customer attrition. It is also referred as loss of clients or customers. The goal of a customer churn model is to identify signaling behavior of at risk customers. Intelligencia’s model investigates the worth of a client's internal transactional to predict the target variable of disengagement via a data mining exercise. Intelligencia attempts to extract significant predictors of long-term customer loyalty using lifecycle metrics/data. 

For social gaming companies, Intelligencia's model outputs predictions on demand for each player's likelihood of churn. It also provides information about the risk factors that affect the exit of players as well. Additionally, the approach not only gives a list of possible churners, but also produces, for every player, a survival probability function that will let reveal how the probability of churning is varying as a function of time. This feature lets a company distinguish between various levels of loyalty profiles, whether they are upcoming, near-future and far-future churners, and the variables that influence this survival behavior. From this survival function, the median survival time is extracted and used as a life expectancy threshold. This feature lets us label players as being at risk of churning so that the social gaming company can take action beforehand to retain valuable players, and ultimately improve game development to enhance player satisfaction.

With any data-mining problem, the nature of the data and its richness is what's going to decide the best approach to take so there will need to be preliminary analysis of the input data to understand what is available, such as a derivation of metrics. These metrics can then be tested for their likelihood of predicting punter success/profitability. The inputs would then be narrowed down to significant predictors that could be fed into a prediction algorithm. Intelligencia will investigate such predictive analytical processes as neural networks, decision trees, and logistic regression, amongst others things.

Customer Churn models can also be helpful in understanding the customer buying journey, which could help decrease customer acquisition costs, as well as provide insights into increasing revenue per customer, and improving customer service.

© 2017-2018 Intelligencia Limited. All Rights Reserved.

Contact

MACAU:

Rua da Esrela, No. 8, Macau

Macau: +853 6616 1033

 

HONG KONG:

505 Hennessy Road, #613, Causeway Bay

HK: +852 5196 1277

andrew.pearson@intelligencia.co