Data normalization and irregularity detection system

1. A computing system configured to provide analysis of claim information, the system comprising:

a computer readable storage medium having program instructions embodied therewith; and

one or more processors configured to execute the program instructions to cause the computing system to:

receive a file comprising a plurality of records, the plurality of records comprising: (i) a first record associated with a first person and a first provider, and (ii) a second record associated with a second person and a second provider, the first person different from the second person;

determine a first format of the plurality of records;

convert, from the first format into a standard format, (i) the first record to a first data item and (ii) the second record to a second data item, wherein converting the first record to the first data item further comprises:

identifying a code associated with a first column header and a data value of the first record; and

assigning the code to a data field in the first data item;

cause presentation, in a first user interface, of a statistical measure based at least in part on a plurality of data items comprising at least one of the first data item or the second data item;

receive, in the first user interface, user input indicating a selection of the first provider;

determine, from the plurality of data items, a subset of data items associated with the first provider, the subset of data items (i) including the first data item and (ii) excluding the second data item; and

cause presentation, in a second user interface, of a time series plot based at least in part on the subset of data items associated with the first provider.

2. The computing system according to claim 1 , wherein the file further comprises a plurality of column headers, and wherein converting the first record to the first data item further comprises:

mapping the first column header of the plurality of column headers to the data field in the first data item.

3. The computing system according to claim 1 , wherein

converting the first record to the first data item further comprises replacing or annotating a code associated with the first record with natural language.

4. The computing system according to claim 1 , wherein

determining the first format is based at least partially on format information associated with previous records.

5. The computing system according to claim 1 , wherein converting the first record to the first data item further comprises resolving or dereferencing a provider-specific code.

6. The computing system according to claim 1 , wherein the first user interface further comprises a histogram based at least in part on the plurality of data items.

7. The computing system according to claim 1 , wherein the first user interface further comprises one or more visual indicators.

8. A computer-implemented method for providing analysis of claim information, the method comprising:

receiving a file comprising a plurality of records, the plurality of records comprising: (i) a first record associated with a first person and a first provider, and (ii) a second record associated with a second person and a second provider, the first person different from the second person;

determining a first format of the plurality of records;

converting, from the first format into a standard format, (i) the first record to a first data item and (ii) the second record to a second data item, wherein converting the first record to the first data item further comprises:

identifying a code associated with a first column header and a data value of the first record; and

assigning the code to a data field in the first data item;

causing presentation, in a first user interface, of a statistical measure based at least in part on a plurality of data items comprising at least one of the first data item or the second data item;

receiving, in the first user interface, user input indicating receive a selection of the first provider;

determining, from the plurality of data items, a subset of data items associated with the first provider, the subset of data items (i) including the first data item and (ii) excluding the second data item; and causing presentation, in a second user interface, of a visualization based at least in part on the subset of data items associated with the first provider, and

wherein the method is performed by one or more computer hardware processors.

9. The method according to claim 8 , wherein the file further comprises a plurality of column headers, and wherein converting the first record to the first data item further comprises:

mapping the first column header of the plurality of column headers to the data field in the first data item.

10. The method according to claim 8 , wherein converting the first record to the first data item further comprises replacing or annotating a code associated with the first record with natural language.

11. The method according to claim 8 , wherein determining the first format is based at least partially on format information associated with previous records.

12. The method according to claim 8 , wherein converting the first record to the first data item further comprises resolving or dereferencing a provider-specific code.

13. The method according to claim 8 , wherein the visualization comprises a time series plot.

14. The method according to claim 8 , wherein the visualization comprises a histogram.

15. The method according to claim 8 , wherein the visualization comprises a chart.