# US 2014/0207775 A1 · On the fly data binning

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2014/0207775 A1
- Document ID: US20140207775A1
- Status: Published application
- Kind: A1
- Application number: 14/222,069
- Filed: 2014-03-21
- Published: 2014-07-24
- Earliest claimed: 2012-12-19
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Louis L. KITTOCK; Jon K. PECK; Vladimir E. SHKLOVER
- Web page: https://patentgrep.com/patent/US20140207775A1

## CPC

- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- G06F 16/22: Indexing; Data structures therefor; Storage structures
- G06F 16/90: Details of database functions independent of the retrieved data types
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A computer-implemented method, a computer-implemented system, and a computer program product for data binning are disclosed. In a first aspect, the computer-implemented method comprises in response to a determination that a data value is greater than an estimated maximum data value, calculating a new bin position for the data value by adding multiples of a bin width to the estimated maximum data value until a bin where the data value belongs is found.

## Claims

### Claim 1

A computer-implemented method for data binning, the computer-implemented method comprising:
in response to a determination that a data value is greater than an estimated maximum data value, calculating a new bin position for the data value by adding multiples of a bin width to the estimated maximum data value until a bin where the data value belongs is found.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
in response to a determination that a data value is lesser than an estimated minimum data value, calculating a new bin position for the data value by subtracting multiples of a bin width from the estimated minimum data value until a bin where the data value belongs is found.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein the estimated maximum data value and the estimated minimum data value are determined by a random data sampling to provide an estimated range.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, wherein the bin width is determined using the estimated range and a desired number of bins.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein the bin comprises a number of data values within the bin and a mean of the data values.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, further comprising:
updating the number of data values within the bin and the mean of the data values each time a data value is placed in the bin.

### Claim 7 (depends on 3)

The computer-implemented method of claim 3, wherein bins outside the estimated range are outlier bins that are stored in a separate hash map container.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein the data binning creates a distributional summary of a numeric variable with unknown data range using one data pass.
