Quantum Leap Analyst is organized into four modules aligned with the logical steps in the analytical process:


The Data Module enables you to select the data source, optionally configure the data type (e.g. numeric, categorical or date/time), load the data, view and qualify the data, and obtain basic statistical insight such as data distribution, counts, sums, averages etc.


In exploration, you are driving Quantum Leap Analyst’s analytical engine to obtain specific information that may help shed light on the problem at hand. Exploration includes several techniques to obtain such detailed insight: find correlations between attributes, rank attributes in terms of importance against a specific target attribute, compare attributes against one another, compare data subsets against each other, examine distributions and isolate outliers, identify data subsets with similar traits, as well as popular reporting and visualization functions.


Quantum Leap Analyst includes a patented technology that automatically detects patterns that are informative against a given target. So if you are trying to obtain unbiased insight into a given attribute (the target), Quantum Leap Analyst will not only detect which attributes are most relevant and informative against that target but also divide the data into the corresponding subsets.


Predictive models are built automatically in Quantum Leap Analyst. The models are pattern based and can be used for what-if analysis with existing or new data, as well as allow you to explore alternative actions in the context of possible, future scenarios.