Cause-of-viewer-disengagement estimating apparatus, cause-of-viewer-disengagement estimating method and program

1. A viewing abandonment factor estimation device comprising:

a memory storing program instructions; and

a processor configured to execute the stored program instructions, wherein the program instructions

include an estimation model for estimating a factor, the estimation model including a plurality of feature quantities measurable for viewing of a video relevant to an adaptive bit rate video distribution as inputs and the factor of the viewing abandonment in the viewing as an output,

wherein the estimation model comprises a classification tree model comprising a set of classification rules having a tree structure, and

wherein the factor of the viewing abandonment comprises a binary variable that indicates the cause of abandonment for the video.

2. The viewing abandonment factor estimation device according to claim 1 , wherein the processor applies the plurality of feature quantities measured in the viewing to the estimation model to estimate the factor.

3. The viewing abandonment factor estimation device according to claim 1 , wherein the estimation model is a statistical model of a type that performs binary classification or a machine learning model of a type that performs binary classification.

4. The viewing abandonment factor estimation device according to claim 1 , wherein the cause of abandonment for the video comprises a quality of the video or a content of the video.

5. The viewing abandonment factor estimation device according to claim 1 , wherein estimating the factor comprises the estimation model evaluating whether each of the plurality of feature quantities satisfies a threshold for each of the plurality of feature quantities.

6. A viewing abandonment factor estimation method executed by a computer including a memory and processor, the method comprising:

estimating a factor by an estimation model, the estimation model being stored on the memory and executed by the processor, the estimation model including a plurality of feature quantities measurable for viewing of a video relevant to an adaptive bit rate video distribution as inputs and the factor of the viewing abandonment in the viewing as an output,

wherein the estimation model comprises a classification tree model comprising a set of classification rules having a tree structure, and

wherein the factor of the viewing abandonment comprises a binary variable that indicates the primary cause of abandonment for the video.

7. The viewing abandonment factor estimation method according to claim 6 , wherein the including includes applying the plurality of feature quantities measured in the viewing to the estimation model to estimate the factor.

8. The viewing abandonment factor estimation method according to claim 6 , wherein the estimation model is a statistical model of a type that performs binary classification or a machine learning model of a type that performs binary classification.

9. A non-transitory computer-readable recording medium having computer-readable instructions stored thereon, which when executed, cause a computer including a memory and a processor to operate as the viewing abandonment factor estimation device according to claim 1 .