Information processing method, information processing apparatus, and program
An information processing method executed by one or more processors, in which a plurality of models, which are trained by using one or more of datasets including a behavior history of a user on an item, which is collected at each of a plurality of first facilities different from each other, are prepared, and the one or more processors include acquiring a characteristic of a second facility, which is different from the plurality of first facilities and acquiring a characteristic of each of the plurality of first facilities, evaluating a similarity degree between the acquired characteristic of the second facility and the characteristic of the first facility where the dataset, which is used for the training of the model, is collected, and selecting a model suitable for the second facility from among the plurality of models based on the similarity degree.
1 . An information processing method comprising:
preparing a plurality of models, wherein each of the plurality of models is respectively trained by using one or more of datasets including a behavior history of a user on an item, and wherein each of the plurality of models is respectively collected at a different first facility among a plurality of first facilities different from each other; and
causing one or more processors to include:
acquiring a characteristic of a second facility, which is different from the plurality of first facilities and acquiring a characteristic of each of the plurality of first facilities;
evaluating a similarity degree between the acquired characteristic of the second facility and the characteristic of each of the plurality of first facilities; and
selecting a model for the second facility from among the plurality of models based on the similarity degrees, wherein the selected model corresponds to the first facility having a highest similarity degree.
2 . The information processing method according to claim 1 , further comprising:
causing the one or more processors to include extracting statistical information of a dataset of metadata that is an explanatory variable used for the training of the model,
wherein the characteristic includes the statistical information.
3 . The information processing method according to claim 2 ,
wherein the metadata includes at least one of a user attribute or an item attribute.
4 . The information processing method according to claim 1 , further comprising:
causing the one or more processors to include acquiring facility related information other than metadata included in the dataset used for the training of the model,
wherein the characteristic includes the facility related information.
5 . The information processing method according to claim 4 ,
wherein the facility related information is extracted by performing web crawling.
6 . The information processing method according to claim 4 ,
wherein the one or more processors are configured to receive the facility related information via a user interface.
7 . The information processing method according to claim 1 ,
wherein the one or more processors are configured to:
acquire an evaluation value of prediction performance at each of the plurality of first facilities where the dataset, which is used for the training of each of the plurality of models, is collected; and
select a model for the second facility from among the plurality of models based on the similarity degrees and the evaluation values of the prediction performance.
8 . The information processing method according to claim 1 ,
wherein the one or more processors are configured to:
acquire conformity evaluation information indicating an evaluation related to conformity of the model with respect to the second facility, separately from the similarity degrees; and
select a model for the second facility from among the plurality of models based on the similarity degrees and the conformity evaluation information.
9 . The information processing method according to claim 8 ,
wherein the conformity evaluation information includes a result of a questionnaire for a user at the second facility.
10 . The information processing method according to claim 1 , further comprising:
causing the one or more processors to include evaluating,
by using characteristics of a plurality of third facilities for which similarity degrees to the characteristic of each of the plurality of first facilities have been evaluated,
a similarity degree between the characteristic of the second facility and the characteristic of each of the plurality of first facilities based on similarity degrees between the characteristic of the second facility and the characteristics of the plurality of third facilities.
11 . The information processing method according to claim 10 , further comprising:
causing the one or more processors to include storing, in a storage device,
the characteristics of the plurality of third facilities; and
the respective similarity degrees between the characteristic of each of the plurality of facilities and the characteristics of the plurality of third facilities.
12 . The information processing method according to claim 1 ,
wherein the model is a prediction model used in a suggestion system that suggests an item to a user.
13 . The information processing method according to claim 1 , further comprising:
causing the one or more processors to include storing the plurality of models in a storage device.
14 . The information processing method according to claim 13 , further comprising:
causing the one or more processors to include storing the characteristic of each of the plurality of first facilities where the dataset, which is used for the training of each of the models, is collected in the storage device in association with the model.
15 . The information processing method according to claim 1 ,
wherein each of the plurality of first facilities and the second facility is a different group of users.
16 . The information processing method according to claim 1 ,
wherein each of the plurality of first facilities and the second facility is a different working domain.
17 . An information processing apparatus comprising:
one or more processors; and
one or more storage devices in which an instruction executed by the one or more processors is stored,
wherein a plurality of models, wherein each of the plurality of models is respectively trained by using one or more of datasets including a behavior history of a user on an item, and wherein each of the plurality of models is respectively collected at a different first facility among a plurality of first facilities different from each other, are stored in the storage device, and
the one or more processors are configured to:
acquire a characteristic of a second facility, which is different from the plurality of first facilities and acquire a characteristic of each of the plurality of first facilities;
evaluate a similarity degree between the acquired characteristic of the second facility and the characteristic of each of the plurality of first facilities; and
select a model for the second facility from among the plurality of models based on the similarity degrees, wherein the selected model corresponds to the first facility having a first similarity degree.
18 . A non-transitory, computer-readable tangible recording medium which records thereon a program for causing, when read by a computer, the computer to realize:
a function of storing a plurality of models, wherein each of the plurality of model is respectively trained by using one or more of datasets including a behavior history of a user on an item, and wherein each of the plurality of models is respectively collected at a different first facility among a plurality of first facilities different from each other;
a function of acquiring a characteristic of a second facility, which is different from the plurality of first facilities and acquiring a characteristic of each of the plurality of first facilities;
a function of evaluating a similarity degree between the acquired characteristic of the second facility and the characteristic of each of the plurality of first facilities; and
a function of selecting a model for the second facility from among the plurality of models based on the similarity degrees, wherein the selected model corresponds to the first facility having a highest similarity degree.