# US 2014/0156649 A1 · Automatic Detection of Patterns and Inference in a Dataset > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2014/0156649 A1 - Document ID: US20140156649A1 - Status: Published application - Kind: A1 - Application number: 13/692,713 - Filed: 2012-12-03 - Published: 2014-06-05 - Earliest claimed: 2012-12-03 - Assignees: Sap SE - Applicants: Sap AG - Inventors: Arindam Bhattacharjee; Ganesh Vaitheeswaran; Prasanna Bhat Mavinakuli - Web page: https://patentgrep.com/patent/US20140156649A1 ## CPC - G06F 16/24578: {using ranking} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Techniques allow automatic identification of statistically significant attribute combinations in a dataset, and provide users with an understanding thereof including starting points for further analysis. Statistically significant combinations may be obtained from large data sets by limiting combinations to four or fewer attributes. The combinations obtained may be ranked to differentiate patterns, e.g. according to factors such as error ratio, decision tree depth, occurrences, and number of attributes. Still further insights may be achieved by ranking attributes according to the number of statistically significant combinations in which they appear. For useful visualization of statistically significant information within the patterns, only those having at least one measure/numeric may analyzed for further insight (e.g. by an outlier algorithm) and presented as output in a chart (e.g. pie, bar) form. The decision tree approach of various embodiments may facilitate ‘What if’ analysis of the data, as well as obtaining the reverse inference. ## Claims ### Claim 1 A computer-implemented method comprising: providing a data set comprising data organized in rows and columns; generating a decision tree comprising a combination of between 2-4 columns; evaluating a statistical significance of the combination of columns; and ranking the combination of columns. ### Claim 2 (depends on 1) A method as in claim 1 further comprising: generating an inference based upon a ranked combination of columns comprising at least one numerical measure; and displaying the inference as a chart comprising the numerical measure. ### Claim 3 (depends on 1) A method as in claim 1 wherein ranking the combination of columns considers a factor selected from: a decision tree depth, an error ratio, a number of occurrences, a number of attributes, and a boosting factor. ### Claim 4 (depends on 1) A method as in claim 1 wherein the combinations of columns include a continuous variable, and the method further comprises discretizing the continuous variable. ### Claim 5 (depends on 1) A method as in claim 1 further comprising creating a READ ONLY procedure in order to generate the decision tree. ### Claim 6 (depends on 1) A method as in claim 1 further comprising: based upon the ranked combination of columns, performing additional analysis selected from: ranking of columns; performing a “What if” analysis; and obtaining a reverse inference. ### Claim 7 A non-transitory computer readable storage medium embodying a computer program for performing a method, said method comprising: providing a data set comprising data organized in rows and columns; generating a decision tree comprising a combination of between 2-4 columns; evaluating a statistical significance of the combination of columns; and ranking the combination of columns. ### Claim 8 (depends on 7) A non-transitory computer readable storage medium as in claim 7 wherein the method further comprises: generating an inference based upon a ranked combination of columns comprising at least one numerical measure; and displaying the inference as a chart comprising the numerical measure. ### Claim 9 (depends on 7) A non-transitory computer readable storage medium as in claim 7 wherein ranking the combination of columns considers a factor selected from: a decision tree depth, an error ratio, a number of occurrences, a number of attributes, and a boosting factor. ### Claim 10 (depends on 7) A non-transitory computer readable storage medium as in claim 7 wherein the combinations of columns include a continuous variable, and the method further comprises discretizing the continuous variable. ### Claim 11 (depends on 7) A non-transitory computer readable storage medium as in claim 7 wherein the method further comprises creating a READ ONLY procedure in order to generate the decision tree. ### Claim 12 (depends on 7) A non-transitory computer readable storage medium as in claim 7 wherein the method further comprises: based upon the ranked combination of columns, performing additional analysis selected from: ranking of columns; performing a “What if” analysis; and obtaining a reverse inference. ### Claim 13 A computer system comprising: one or more processors; a software program, executable on said computer system, the software program configured to: provide a data set comprising data organized in rows and columns; generate a decision tree comprising a combination of between 2-4 columns; evaluate a statistical significance of the combination of columns; and rank the combination of columns. ### Claim 14 (depends on 13) A computer system as in claim 13 wherein the software program is further configured to: generate an inference based upon a ranked combination of columns comprising at least one numerical measure; and display the inference as a chart comprising the numerical measure. ### Claim 15 (depends on 13) A computer system as in claim 13 wherein ranking the combination of columns considers a factor selected from: a decision tree depth, an error ratio, a number of occurrences, a number of attributes, and a boosting factor. ### Claim 16 (depends on 13) A computer system as in claim 13 wherein the combinations of columns include a continuous variable, and the method further comprises discretizing the continuous variable. ### Claim 17 (depends on 13) A computer system as in claim 13 wherein the software program is further configured to: based upon the ranked combination of columns, perform additional analysis selected from: ranking of columns; performing a “What if” analysis; and obtaining a reverse inference. ### Claim 18 (depends on 13) A computer system as in claim 13 further comprises creating a READ ONLY procedure in order to generate the decision tree.