Standard

Forecasting and XAI for Applications Usage in OS. / Ma, Ruimin; Zhang, Yuyi ; Liu, Jing ; Li, Yin ; Petrosian, Ovanes ; Krinkin, Kirill V.

Machine Learning and Artificial Intelligence. IOS Press, 2022. p. 17-27 (Frontiers in Artificial Intelligence and Applications; No. 360).

Research output: Chapter in Book/Report/Conference proceedingArticle in an anthologyResearchpeer-review

Harvard

Ma, R, Zhang, Y, Liu, J, Li, Y, Petrosian, O & Krinkin, KV 2022, Forecasting and XAI for Applications Usage in OS. in Machine Learning and Artificial Intelligence. Frontiers in Artificial Intelligence and Applications, no. 360, IOS Press, pp. 17-27. https://doi.org/10.3233/FAIA220419

APA

Ma, R., Zhang, Y., Liu, J., Li, Y., Petrosian, O., & Krinkin, K. V. (2022). Forecasting and XAI for Applications Usage in OS. In Machine Learning and Artificial Intelligence (pp. 17-27). (Frontiers in Artificial Intelligence and Applications; No. 360). IOS Press. https://doi.org/10.3233/FAIA220419

Vancouver

Ma R, Zhang Y, Liu J, Li Y, Petrosian O, Krinkin KV. Forecasting and XAI for Applications Usage in OS. In Machine Learning and Artificial Intelligence. IOS Press. 2022. p. 17-27. (Frontiers in Artificial Intelligence and Applications; 360). https://doi.org/10.3233/FAIA220419

Author

Ma, Ruimin ; Zhang, Yuyi ; Liu, Jing ; Li, Yin ; Petrosian, Ovanes ; Krinkin, Kirill V. / Forecasting and XAI for Applications Usage in OS. Machine Learning and Artificial Intelligence. IOS Press, 2022. pp. 17-27 (Frontiers in Artificial Intelligence and Applications; 360).

BibTeX

@inbook{6fa5c0cfdb0144f3bde3662afa030be8,
title = "Forecasting and XAI for Applications Usage in OS",
abstract = "In the context of digital informatization, the Internet is changing the way of human existence. The rapid development of the Internet has promoted the use of smartphones in people{\textquoteright}s daily lives, and at the same time, a large number of applications running on different operating system environments have appeared on the market. Predicting the duration of application usage is crucial for the management planning of related companies and the good life of users. In this work, a dataset containing time series of user application usage information is considered and the problem of “application usage” forecast is being addressed. The dataset used in this work is based on reliable and realistic user records of the usage of the application. Firstly, this paper investigates suitable forecast models for application development on the applied user usage time dataset, which includes neural network algorithms and ensemble algorithms, among others. Then, an Explainable Artificial Intelligence Approach (SHAP) is introduced to explain the selected optimal forecast models, thus enhancing user trust of the forecasting models. The forecast results show that the ensemble models perform better in the time series dataset of user application usage information, especially LightGBM has more obvious advantages. Explanation results show that the frequency of use of the target variables, category and lagged nature are important features in the forecast of the application dataset.",
keywords = "Time-series forecasting, Ensemble model, Neural network, Explainable AI (XAI",
author = "Ruimin Ma and Yuyi Zhang and Jing Liu and Yin Li and Ovanes Petrosian and Krinkin, {Kirill V.}",
year = "2022",
doi = "10.3233/FAIA220419",
language = "English",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS Press",
number = "360",
pages = "17--27",
booktitle = "Machine Learning and Artificial Intelligence",
address = "Netherlands",

}

RIS

TY - CHAP

T1 - Forecasting and XAI for Applications Usage in OS

AU - Ma, Ruimin

AU - Zhang, Yuyi

AU - Liu, Jing

AU - Li, Yin

AU - Petrosian, Ovanes

AU - Krinkin, Kirill V.

PY - 2022

Y1 - 2022

N2 - In the context of digital informatization, the Internet is changing the way of human existence. The rapid development of the Internet has promoted the use of smartphones in people’s daily lives, and at the same time, a large number of applications running on different operating system environments have appeared on the market. Predicting the duration of application usage is crucial for the management planning of related companies and the good life of users. In this work, a dataset containing time series of user application usage information is considered and the problem of “application usage” forecast is being addressed. The dataset used in this work is based on reliable and realistic user records of the usage of the application. Firstly, this paper investigates suitable forecast models for application development on the applied user usage time dataset, which includes neural network algorithms and ensemble algorithms, among others. Then, an Explainable Artificial Intelligence Approach (SHAP) is introduced to explain the selected optimal forecast models, thus enhancing user trust of the forecasting models. The forecast results show that the ensemble models perform better in the time series dataset of user application usage information, especially LightGBM has more obvious advantages. Explanation results show that the frequency of use of the target variables, category and lagged nature are important features in the forecast of the application dataset.

AB - In the context of digital informatization, the Internet is changing the way of human existence. The rapid development of the Internet has promoted the use of smartphones in people’s daily lives, and at the same time, a large number of applications running on different operating system environments have appeared on the market. Predicting the duration of application usage is crucial for the management planning of related companies and the good life of users. In this work, a dataset containing time series of user application usage information is considered and the problem of “application usage” forecast is being addressed. The dataset used in this work is based on reliable and realistic user records of the usage of the application. Firstly, this paper investigates suitable forecast models for application development on the applied user usage time dataset, which includes neural network algorithms and ensemble algorithms, among others. Then, an Explainable Artificial Intelligence Approach (SHAP) is introduced to explain the selected optimal forecast models, thus enhancing user trust of the forecasting models. The forecast results show that the ensemble models perform better in the time series dataset of user application usage information, especially LightGBM has more obvious advantages. Explanation results show that the frequency of use of the target variables, category and lagged nature are important features in the forecast of the application dataset.

KW - Time-series forecasting

KW - Ensemble model

KW - Neural network

KW - Explainable AI (XAI

U2 - 10.3233/FAIA220419

DO - 10.3233/FAIA220419

M3 - Article in an anthology

T3 - Frontiers in Artificial Intelligence and Applications

SP - 17

EP - 27

BT - Machine Learning and Artificial Intelligence

PB - IOS Press

ER -

ID: 104166212