An Analysis of your data might reveal unused knowledge and ease decisions for your business. We offer the complete range of statistical data analysis and modeling, including...

• calculating statistics and significance of the results,
• prediction or classification model building,
• automatic reporting and graphical representation of results,
• analytical reports,
• checking the validity of models,
• building models which can be used for prediction purposes.

Data are not Information

Data are not information! Methods of data analysis are used in a wide variety of occupations and help people identify, study, and solve many complex problems. In the business and economic world, these methods enable decision makers and managers to make informed and better decisions in uncertain situations.

Vast amounts of statistical information are available in today's global and economic environment because of continual improvements in computer technology. To compete successfully globally, managers and decision makers must be able to understand the information and use it effectively. This is a premise for making educated decisions in the business world.

Things are simple if one has a question in mind and is able to collect data necessary in order to give an informed answer to this question. Often, however, data is collected without such a question in mind. In other cases, only a vague idea exists which type of knowledge might be hidden in the data. On the other hand, data collection has become easy almost to the point of triviality.´ Piles of data are collected and important knowledge is often hidden without anybody knowing.

Analyzing the Data

Data analysis provides two very different types of methods: unsupervised or exploratory analysis methods and supervised or predictive analysis methods. The goal for unsupervised analysis methods is to find inherent structures and patterns in your data you were not aware of. Clustering methods like k-Means, EM-Clustering, or hierarchical clustering deliver such patterns and are also able to identify outliers and interesting points which can not be explained by simple and well-known connections. Other unsupervised analysis methods include frequent item set mining (Apriori, FPGrowth, Closed Sets) which can be used to identify related items in your data and deliver useful rules. A famous application for this type of methods is mining databases of transactions for items often sold together.

In contrast to unsupervised analysis methods, the second large group of analysis methods are used it there is a concrete question which should be answered. These supervised learning methods are able to classify items, e.g. in good and in bad customers, or can predict future trends. Well known methods for this type of analysis are Decision Trees, Neural Networks, Support Vector Machines, and Prediction Rule Learners.

Reporting the Results

The analysis of data and the application of large scale machine learning methods characteristics of your data, inherent patterns, or prediction models will be found. The results may be reported in the form of a table, a graph or a set of percentages. Because often not the entire population was examined, the reported results must also reflect the uncertainty through the use of probability statements and intervals of values. The concrete form of reporting depends on your personal preferences and might be textual and/or graphical.

To conclude, a critical aspect of managing any organization is planning for the future. Good judgment, intuition, and an awareness of the state of the economy may give a manager a rough idea or "feeling" of what is likely to happen in the future. Data analysis helps managers forecast and predict future aspects of a business operation. The most successful managers and decision makers are the ones who can understand the information and use it effectively.

Contact us

Please contact us if you are interested in an in-depth analysis of your data.