How can we apply analytical techniques from other sectors in marketing? (Part 1)
Over the month of November Brightblue R&D team have been looking at analytical techniques from other industries and how they can be applied within the Marketing industry. In this part of this topic we will discuss anomaly detection.
In this course of three articles we will share with you 3 of those techniques that can be used to provide the most amount of value from businesses data.
Part One: Anomaly Detection
Have you ever wondered how your bank was able to identify that a particular purchase using your card was not you?
Every transaction, withdrawal and transfer of cash you make serves as a data-point for your Bank’s algorithm in order to learn about your spending profile. Hence, once any unusual activity outside of what is deemed normal takes place, the bank is able to identify this and take action immediately.
Below is a simple example of a computer learning about the data it is fed and in turn creating a confidence interval (shown by the light blue region) of what it considers to be usual behaviour. Once the data series falls outside of this area (shown by the light blue region), the relevant users would be notified and the necessary steps can be taken instantly.
Figure 1: Confidence interval
Think of this as the revenue data of an e-commerce company. The highlighted section demonstrates anomalous performance which can be looked into without delay for example a website disruption.
Real time anomaly detection is critical for e-commerce due to the fact that it can detect and alert on costly issues instantly, preventing long term negative effects from occurring.
Traditionally, the marketing industry have deployed manual means of detection of anomalies by reviewing weekly data. This can be time intensive and leaves room for human error which can be eradicated when automating this process.
Therefore, utilising automated anomaly detection can save business time and increase response times during peak or fallow periods.
Brightblue Consulting are a London based consultancy which help businesses drive incremental profit from their data. We provide predictive analytics that enable clients to make informed decisions based on data and industry knowledge. Through Market Mix Modelling, a strand of Econometrics, Brightblue has a proven track record showing a 30% improvement in marketing Return on Investment for clients’ spend. If you are interested to find out more please contact us through email by clicking here and one of our consultants will get back to you shortly.