Find hidden patterns

Data mining is about finding hidden patterns.  Wikipedia defines it as "the process of extracting patterns from large data sets by combining methods from statistics and artificial intelligence with database management."  Mariner leverages Microsoft's SQL Server Data Platform for Data Mining. 

Our process

Define the problem: This step includes analyzing business requirements, defining the scope of the problem, defining the metrics by which the model will be evaluated, and defining specific objectives for the data mining project.

Prepare Data: Data can be scattered across a company and stored in different formats or may contain inconsistencies such as incorrect or missing entries.  Mariner's greatest strength lies in being able to assemble and integrate various sources of data in a smart and elegant way. 

Explore: Exploration techniques include calculating the minimum and maximum values, calculating mean and standard deviations and looking at the distribution of the data. 

Build Models: In this step, our deep understanding of the Microsoft Analysis Services platform provides us with the ability to create a good model or mining structure.  The mining structure is a shell, it defines the source of data, but does not contain any data until it is processed.

Validate Models: Before you deploy a model into a production environment, you will want to test how well the model performs.  Often we create multiple models with different configurations and test all models to see which yields the best results for your problem and your data.

Deploy & Update: At this stage, we could use the models in a variety of ways: Creating predictions, reporting, embedding models into applications, with SQL Server Integration Services and so on.