- Analytics
- Churn / Attrition and Retention / Loyalty Models
- Clustering
- Customer Analytics
- Customer Life-Cycle Analysis
- Customer Segmentation
- Customer Value Models
- Data Analysis
- Data Mining
- Data Segmentation
- Decision Trees
- Market Analysis
- Market Basket Analysis
- Predictive Modelling
- Profiling
- Recency, Frequency, Value (RFV) Analysis
- Response Analysis and Models
Data Mining
Data mining is the process of extracting patterns from data sets. Its aim is to establish relationships where none had been identified previously.
Data mining is used in a number of disciplines that include areas such as fraud detection, mathematics, science and marketing. Data mining parameters in include:
- Association - looking for patterns where one event is connected to another event
- Sequence or path analysis - looking for patterns where one event leads to another later event
- Classification - looking for new patterns
- Clustering - finding and visually documenting groups of facts not previously known
- Forecasting - discovering patterns in data that can lead to reasonable predictions about the future (predictive analytics)
In marketing terms, data mining is an over-arching term that includes all sorts of data analysis, such as profiling, predictive analysis customer segmentation, exploratory analysis, initial data audits, customer insight and so on.
Data mining is commonly used in marketing to provide information about different aspects of customer data sets. Its goal is to allow a company to improve its marketing, sales and customer support through a better understanding of its customers. Whilst there are large amounts of data available to every company, this data is not always turned into actionable information. This is what data mining seeks to provide.
Data mining, as all data analysis, comes with a warning that the value and reliability of the information and insight provided is only as effective as the raw data that creates it.
From the start it is very important when conducting data mining to be aware of any bias in the data population being analysed. The reason for this is that if there is a particular bias, then the results provided may not be indicative – they may well be non-representative. The outcome of this is that the discovery of a particular pattern in a particular set of data does not necessarily mean that pattern is representative of the whole population from which that data was drawn. Consequently, great emphasis is placed in data mining on the verification and validation of patterns on other samples of data.