Analyzing changes in web analytics metrics

• US 9,521,205 B1
• Filed: 08/01/2011
• Issued: 12/13/2016
• Est. Priority Date: 08/01/2011
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Ni, Jiang, Liao, Lin, Liebert, Elizabeth L.
• Primary Examiner(s): Woolcock, Madhu
• Application Number:
  US13/136,507
• Time in Patent Office: 1,961 Days
• Field of Search: 709/224, 705/14.45
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: H04L 43/08 Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for analyzing changes in web analytics metrics. In one aspect, a method includes identifying a change in a web analytics metric for a website over a period of time, the web analytics metric being based at least in part on visitor data for the website over the period of time; computing a respective segment contribution score for each of a plurality of segments of the web analytics metric, wherein a segment contribution score for a particular segment is based at least in part on a comparison between a value of the web analytics metric and a value of the particular segment during the period of time; and identifying one or more of the plurality of segments as contributing to the change in the web analytics metric based on the respective segment contribution scores.

Claims

1. A method comprising:

obtaining, by one or more data processing apparatus, from a data store, and over a network, visitor data collected from one or more client devices accessing, over the network, one or more remote servers that manage websites visited by the one or more client devices;

identifying, by the one or more data processing apparatus, a change in a web analytics metric for a given website over a period of time, the web analytics metric being based at least in part on the visitor data associated with the one or more client devices accessing, over the network, the one or more remote servers to visit the given website during the period of time;

computing, by the one or more data processing apparatus, a respective segment contribution score for each of a plurality of segments of the web analytics metric, wherein each of the plurality of segments of the web analytics metric is defined by a respective set of one or more attribute-value pairs such that values of the segment are determined only from visits to the given website that have attribute values that satisfy each of the attribute-value pairs that define the segment, and wherein computing the respective segment contribution score for each of the plurality of segments comprises;

determining a first comparison between (i) a value of the web analytics metric at an earliest time in the period of time and (ii) a value of the segment at the earliest time in the period of time,

determining a second comparison between (iii) a value of the web analytics metric at a latest time in the period of time and (iv) a value of the segment at the latest time in the period of time, and

computing the respective segment contribution score for each of the plurality of segments of the web analytics metric from the first comparison and the second comparison; and

identifying, by the one or more data processing apparatus, one or more of the plurality of segments as contributing to the change in the web analytics metric based on the respective segment contribution scores,

wherein the web analytics metric is an additive metric and wherein the respective segment contribution score for each of the plurality of segments is equal to;

VS_t2/V_t2−

VS_t1/V_t1, or

k*(VS_t2−

V_t2)WS_t2−

(VS_t1−

V_t1)WS_t1, and

wherein V_t1 is the value of the web analytics metric at the earliest time, V_t2 is the value of the web analytics metric at the latest time, VS_t1 is the value of the segment at the earliest time, VS_t2 is the value of the segment at the latest time, WS_t1 is a value of a weight time series of the segment at the earliest time, WS_t2 is a value of the weight time series of the segment at the latest time, and k is a normalization constant.

2. The method of claim 1, wherein the identifying one or more of the plurality of segments comprises:

ranking the plurality of segments according to the respective segment contribution scores; and

identifying one or more of the plurality of segments as contributing to the change in the web analytics metric based on the ranking.

3. The method of claim 1, further comprising, for each of the identified one or more of the plurality of segments, computing a probability that the identified segment caused the change in the web analytics metric based on the respective segment contribution score for the identified segment.

4. The method of claim 1, further comprising providing data identifying the identified one or more of the plurality of segments for presentation in a user interface.

5. The method of claim 1, further comprising determining the plurality of segments of the web analytics metric, and wherein determining the plurality of segments comprises:

identifying a plurality of candidate segments of the web analytics metric, each candidate segment being computed only from visits to the given website that have attribute values that satisfy one or more respective attribute-value pairs; and

selecting one or more candidate segments that each have a number of visits that exceeds a threshold value.

6. The method of claim 1, wherein the plurality of segments includes single-dimensional segments and multi-dimensional segments.

7. A computer-readable storage device having stored thereon instructions, which, when executed by one or more data processing apparatus, cause the one or more data processing apparatus to perform operations comprising:

obtaining, by the one or more data processing apparatus, from a data store, and over a network, visitor data collected from one or more client devices accessing, over the network, one or more remote servers that manage websites visited by the one or more client devices;

identifying, by the one or more data processing apparatus, a change in a web analytics metric for a given website over a period of time, the web analytics metric being based at least in part on the visitor data associated with the one or more client devices accessing, over the network, the one or more remote servers to visit the given website during the period of time;

computing, by the one or more data processing apparatus, a respective segment contribution score for each of a plurality of segments of the web analytics metric, wherein each of the plurality of segments of the web analytics metric is defined by a respective set of one or more attribute-value pairs such that values of the segment are determined only from visits to the given website that have attribute values that satisfy each of the attribute-value pairs that define the segment, and wherein computing the respective segment contribution score for each of the plurality of segments comprises;

determining a first comparison between (i) a value of the web analytics metric at an earliest time in the period of time and (ii) a value of the segment at the earliest time in the period of time,

determining a second comparison between (iii) a value of the web analytics metric at a latest time in the period of time and (iv) a value of the segment at the latest time in the period of time, and

computing the respective segment contribution score for each of the plurality of segments of the web analytics metric from the first comparison and the second comparison; and

identifying, by the one or more data processing apparatus, one or more of the plurality of segments as contributing to the change in the web analytics metric based on the respective segment contribution scores,

wherein the web analytics metric is an additive metric and wherein the respective segment contribution score for each of the plurality of segments is equal to;

VS_t2/V_t2−

VS_t1/V_t1, or

k*(VS_t2−

V_t2)WS_t2−

(VS_t1−

V_t1)WS_t1, and

wherein V_t1 is the value of the web analytics metric at the earliest time, V_t2 is the value of the web analytics metric at the latest time, VS_t1 is the value of the segment at the earliest time, VS_t2 is the value of the segment at the latest time, WS_t1 is a value of a weight time series of the segment at the earliest time, WS_t2 is a value of the weight time series of the segment at the latest time, and k is a normalization constant.

8. The computer-readable storage device of claim 7, wherein the identifying one or more of the plurality of segments comprises:

ranking the plurality of segments according to the respective segment contribution scores; and

identifying one or more of the plurality of segments as contributing to the change in the web analytics metric based on the ranking.

9. The computer-readable storage device of claim 7, the operations further comprising, for each of the identified one or more of the plurality of segments, computing a probability that the identified segment caused the change in the web analytics metric based on the respective segment contribution score for the identified segment.

10. The computer-readable storage device of claim 7, the operations further comprising determining the plurality of segments of the web analytics metric, and wherein the determining the plurality of segments comprises:

identifying a plurality of candidate segments of the web analytics metric, each candidate segment being computed only from visits to the given website that have attribute values that satisfy one or more respective attribute-value pairs; and

selecting one or more candidate segments that each have a number of visits that exceeds a threshold value.

11. A system comprising:

one or more data processing apparatus; and

a computer-readable storage device having stored thereon instructions that, when executed by the one or more data processing apparatus, cause the one or more data processing apparatus to perform operations comprising;

obtaining, by the one or more data processing apparatus, from a data store, and over a network, visitor data collected from one or more client devices accessing, over the network, one or more remote servers that manage websites visited by the one or more client devices;

identifying, by the one or more data processing apparatus, a change in a web analytics metric for a given website over a period of time, the web analytics metric being based at least in part on the visitor data associated with the one or more client devices accessing, over the network, the one or more remote servers to visit the given website during the period of time;

computing, by the one or more data processing apparatus, a respective segment contribution score for each of a plurality of segments of the web analytics metric, wherein each of the plurality of segments of the web analytics metric is defined by a respective set of one or more attribute-value pairs such that values of the segment are determined only from visits to the given website that have attribute values that satisfy each of the attribute-value pairs that define the segment, and wherein computing the respective segment contribution score for each of the plurality of segments comprises;

determining a first comparison between (i) a value of the web analytics metric at an earliest time in the period of time and (ii) a value of the segment at the earliest time in the period of time,

determining a second comparison between (iii) a value of the web analytics metric at a latest time in the period of time and (iv) a value of the segment at the latest time in the period of time, and

computing the respective segment contribution score for each of the plurality of segments of the web analytics metric from the first comparison and the second comparison; and

identifying, by the one or more data processing apparatus, one or more of the plurality of segments as contributing to the change in the web analytics metric based on the respective segment contribution scores,

wherein the web analytics metric is an additive metric and wherein the respective segment contribution score for each of the plurality of segments is equal to;

VS_t2/V_t2−

VS_t1/V_t1, or

k*(VS_t2−

V_t2)WS_t2−

(VS_t1−

V_t1)WS_t1, and

wherein V_t1 is the value of the web analytics metric at the earliest time, V_t2 is the value of the web analytics metric at the latest time, VS_t1 is the value of the segment at the earliest time, VS_t2 is the value of the segment at the latest time, WS_t1 is a value of a weight time series of the segment at the earliest time, WS_t2 is a value of the weight time series of the segment at the latest time, and k is a normalization constant.

12. The system of claim 11, wherein the identifying one or more of the plurality of segments comprises:

ranking the plurality of segments according to the respective segment contribution scores; and

identifying one or more of the plurality of segments as contributing to the change in the web analytics metric based on the ranking.

13. The system of claim 11, the operations further comprising, for each of the identified one or more of the plurality of segments, computing a probability that the identified segment caused the change in the web analytics metric based on the respective segment contribution score for the identified segment.

14. The system of claim 11, further comprising determining the plurality of segments of the web analytics metric, and wherein determining the plurality of segments comprises:

identifying a plurality of candidate segments of the web analytics metric, each candidate segment being computed only from visits to the given website that have attribute values that satisfy one or more respective attribute-value pairs; and

selecting one or more candidate segments that each have a number of visits that exceeds a threshold value.

15. A method comprising:

obtaining, by one or more data processing apparatus, from a data store, and over a network, visitor data collected from one or more client devices accessing, over the network, one or more remote servers that manage websites visited by the one or more client devices;

identifying, by the one or more data processing apparatus, a change in a web analytics metric for a given website over a period of time, the web analytics metric being based at least in part on the visitor data associated with the one or more client devices accessing, over the network, the one or more remote servers to visit the given website during the period of time;

computing, by the one or more data processing apparatus, a respective segment contribution score for each of a plurality of segments of the web analytics metric, wherein the web analytics metric is an additive metric, and wherein the respective segment contribution score for each of the plurality of segments is equal to;

VS_t2/V_t2−

VS_t1/V_t1,

wherein V_t1 is a value of the web analytics metric at an earliest time in the period of time, V_t2 is a value of the web analytics metric at a latest time in the period of time, VS_t1 is a value of the segment at the earliest time, and VS_t2 is a value of the segment at the latest time; and

identifying, by the one or more data processing apparatus, one or more of the plurality of segments as contributing to the change in the web analytics metric based on the respective segment contribution scores.

16. A method comprising:

obtaining by one or more data processing apparatus, from a data store, and over a network, visitor data collected from one or more client devices accessing, over the network, one or more remote servers that manage websites visited by the one or more client devices;

identifying, by the one or more data processing apparatus, a change in a web analytics metric for a given website over a period of time, the web analytics metric being based at least in part on the visitor data associated with the one or more client devices accessing, over the network, the one or more remote servers to visit the given website during the period of time;

computing, by the one or more data processing apparatus, a respective segment contribution score for each of a plurality of segments of the web analytics metric, wherein the web analytics metric is a ratio metric, and wherein the respective segment contribution score for each of the plurality of segments is equal to;

k*(VS_t2−

V_t2)WS_t2−

(VS_t1−

V_t1)WS_t1,

wherein V_t1 is a value of the web analytics metric at an earliest time in the period of time, V_t2 is a value of the web analytics metric at a latest time in the period of time, VS_t1 is a value of the segment at the earliest time, VS_t2 is a value of the segment at the latest time, WS_t1 is a value of a weight time series of the segment at the earliest time, WS_t2 is a value of the weight time series of the segment at the latest time, and k is a normalization constant; and

identifying, by the one or more data processing apparatus, one or more of the plurality of segments as contributing to the change in the web analytics metric based on the respective segment contribution scores.