Quality of Service(QoS)is a key factor for users when choosing cloud services.However,QoS values are often unavailable due to insufficient user evaluations or provider data.To address this,we propose a new QoS predict...Quality of Service(QoS)is a key factor for users when choosing cloud services.However,QoS values are often unavailable due to insufficient user evaluations or provider data.To address this,we propose a new QoS prediction method,Multi-source Feature Two-phase Learning(MFTL).MFTL incorporates multiple sources of features influencing QoS and uses a two-phase learning framework to make effective use of these features.In the first phase,coarse-grained learning is performed using a neighborhood-integrated matrix factorization model,along with a strategy for selecting high-quality neighbors for target users.In the second phase,reinforcement learning through a deep neural network is used to capture interactions between users and services.We conducted several experi-ments using the WS-Dream data set to assess MFTL's performance in predicting response time QoS.The results show that MFTL outperforms many leading QoS prediction methods.展开更多
More and more marketplace platforms choose to use the data gathered from consumers(e.g.,customer search terms,demographics)to provide a data analytics service for third-party sellers,both encouraging innovations and i...More and more marketplace platforms choose to use the data gathered from consumers(e.g.,customer search terms,demographics)to provide a data analytics service for third-party sellers,both encouraging innovations and improving the operations of the latter.Through adopting the data analytics service,a seller can enhance its competitiveness by improving the quality of its products when there is more than one seller offering substitutes.This study develops a game-theoretic model to characterize a scenario with a marketplace platform and two competing sellers that sell substitutable products and decide whether to adopt the data analytics service provided by the platform.Then,we find that a seller's decision of whether or not to purchase the service depends on the competitor's decision and the two sellers'absorptive capacities of knowledge.Furthermore,a seller can benefit from adopting the data analytics service only if the seller has a high absorptive capacity,which can help increase product quality.When only one seller adopts,the platform and competing sellers can benefit from the adoption if this seller's absorptive capacity is high and the other's is moderate.The sellers'interests and social welfare can be aligned unless both sellers'absorptive capacities are low or high.展开更多
Several mobile telecommunication companies(MTCs),such as AT&T,Verizon,and China Mobile,are investing in content services to drive continued growth as the telecom industry has become saturated.In this study,we inve...Several mobile telecommunication companies(MTCs),such as AT&T,Verizon,and China Mobile,are investing in content services to drive continued growth as the telecom industry has become saturated.In this study,we investigate the competition between two MTCs,one of which(MTC 1)provides both data and content services,while the other(MTC 2)provides only data services.We propose a two-stage game-theoretic model to analyze the two MTCs'optimal pricing strategies for data service and content service as well as the investment strategy for the content service.Our analysis reveals that a higher value of value-added service offered by MTC 1 will incentivize it to raise its subscription fee for the content service and induce both MTCs to reduce the prices of their data services,which results in an increased demand for the content service and a decreased demand for MTC 2's data service.As MTC 1 invests further in the quality of the content service,it would benefit from increasing the subscription fee for the content service,and the two MTCs should increase the subscription fee for the data service.However,compared to the decisions in the scenario where MTC 1 does not provide content service,the provision of this service by MTC 1 leads to a lower subscription fee for the two MTCs'data services,an increase in the demand for MTC 1's data service,and a decrease in the demand for MTC 2's data service.These findings reveal that regularly monitoring market competition,as well as adjusting pricing strategies based on market scenarios and the value of services,can enhance competitiveness and long-term profitability for MTCs.展开更多
To infer product fitness information,consumers often consult digital influencers who exert effort to learn and evaluate product features and then propagate information to their followers.However,influencers'recomm...To infer product fitness information,consumers often consult digital influencers who exert effort to learn and evaluate product features and then propagate information to their followers.However,influencers'recommendations are not limited to products that exactly match their expertise,which may lead followers to unfollow them.This study investigates which product(high or low congruence)an influencer should endorse and how much endorsement effort should be exerted.Using a theoretical model,we obtain several interesting results.First,endorsing a low-congruence product can surprisingly benefit the influencer if the penalty per lost follower is moderate or if the influencer has sufficiently high efficiency in reducing the perception error of this product.Second,although the influencer has high expertise in the high-congruence product,she will lose more followers when endorsing it than when endorsing the low-congruence product if a particularly small or large proportion of her followers are potential consumers of the low-congruence product.Third,when the influencer endorses the low-congruence product,the number of new followers increases with the size of the influencer's follower base only when the follower base is small and a large proportion of followers are potential consumers of the low-congruence product.Interestingly,as the size of the follower base increases,the influencer always exerts more effort when endorsing the high-congruence product but will exert less effort in learning about the low-congruence product if a sufficiently small proportion of followers are potential consumers.Finally,after taking consumers'knowledge about product features into account,the main results still hold,and when considering the competition between influencers,we uncover the conditions under which both influencers will choose to endorse the high-congruence product.展开更多
基金National Natural Science Foundation of China(Grants Nos.72394373,72231004,72022012,and 71971153).
文摘Quality of Service(QoS)is a key factor for users when choosing cloud services.However,QoS values are often unavailable due to insufficient user evaluations or provider data.To address this,we propose a new QoS prediction method,Multi-source Feature Two-phase Learning(MFTL).MFTL incorporates multiple sources of features influencing QoS and uses a two-phase learning framework to make effective use of these features.In the first phase,coarse-grained learning is performed using a neighborhood-integrated matrix factorization model,along with a strategy for selecting high-quality neighbors for target users.In the second phase,reinforcement learning through a deep neural network is used to capture interactions between users and services.We conducted several experi-ments using the WS-Dream data set to assess MFTL's performance in predicting response time QoS.The results show that MFTL outperforms many leading QoS prediction methods.
基金supported by the Major Program of National Natural Science Foundation of China(No.72394373)the National Excellent Youth Fund of National Natural Science Foundation of China(No.72022012)the Key Program and General Program of National Natural Science Foundation of China(No.72231004,No.71871155 and No.71971153).Authors are very grateful to the editor and all reviewers whose invaluable comments and suggestions substantially helped improve the quality of our paper.
文摘More and more marketplace platforms choose to use the data gathered from consumers(e.g.,customer search terms,demographics)to provide a data analytics service for third-party sellers,both encouraging innovations and improving the operations of the latter.Through adopting the data analytics service,a seller can enhance its competitiveness by improving the quality of its products when there is more than one seller offering substitutes.This study develops a game-theoretic model to characterize a scenario with a marketplace platform and two competing sellers that sell substitutable products and decide whether to adopt the data analytics service provided by the platform.Then,we find that a seller's decision of whether or not to purchase the service depends on the competitor's decision and the two sellers'absorptive capacities of knowledge.Furthermore,a seller can benefit from adopting the data analytics service only if the seller has a high absorptive capacity,which can help increase product quality.When only one seller adopts,the platform and competing sellers can benefit from the adoption if this seller's absorptive capacity is high and the other's is moderate.The sellers'interests and social welfare can be aligned unless both sellers'absorptive capacities are low or high.
基金supported by the National Natural Science Foundation of China(NO.71971153,NO.72231004,NO.72394373)Laboratory of Computation and Analytics of Complex Management Systems(CACMS,Tianjin University).
文摘Several mobile telecommunication companies(MTCs),such as AT&T,Verizon,and China Mobile,are investing in content services to drive continued growth as the telecom industry has become saturated.In this study,we investigate the competition between two MTCs,one of which(MTC 1)provides both data and content services,while the other(MTC 2)provides only data services.We propose a two-stage game-theoretic model to analyze the two MTCs'optimal pricing strategies for data service and content service as well as the investment strategy for the content service.Our analysis reveals that a higher value of value-added service offered by MTC 1 will incentivize it to raise its subscription fee for the content service and induce both MTCs to reduce the prices of their data services,which results in an increased demand for the content service and a decreased demand for MTC 2's data service.As MTC 1 invests further in the quality of the content service,it would benefit from increasing the subscription fee for the content service,and the two MTCs should increase the subscription fee for the data service.However,compared to the decisions in the scenario where MTC 1 does not provide content service,the provision of this service by MTC 1 leads to a lower subscription fee for the two MTCs'data services,an increase in the demand for MTC 1's data service,and a decrease in the demand for MTC 2's data service.These findings reveal that regularly monitoring market competition,as well as adjusting pricing strategies based on market scenarios and the value of services,can enhance competitiveness and long-term profitability for MTCs.
基金supported by the National Natural Science Foundation of China(Nos.71971153,72231004,72022012,and 71871155)the Shandong Industrial Internet Innovation and Entrepreneurship Community.
文摘To infer product fitness information,consumers often consult digital influencers who exert effort to learn and evaluate product features and then propagate information to their followers.However,influencers'recommendations are not limited to products that exactly match their expertise,which may lead followers to unfollow them.This study investigates which product(high or low congruence)an influencer should endorse and how much endorsement effort should be exerted.Using a theoretical model,we obtain several interesting results.First,endorsing a low-congruence product can surprisingly benefit the influencer if the penalty per lost follower is moderate or if the influencer has sufficiently high efficiency in reducing the perception error of this product.Second,although the influencer has high expertise in the high-congruence product,she will lose more followers when endorsing it than when endorsing the low-congruence product if a particularly small or large proportion of her followers are potential consumers of the low-congruence product.Third,when the influencer endorses the low-congruence product,the number of new followers increases with the size of the influencer's follower base only when the follower base is small and a large proportion of followers are potential consumers of the low-congruence product.Interestingly,as the size of the follower base increases,the influencer always exerts more effort when endorsing the high-congruence product but will exert less effort in learning about the low-congruence product if a sufficiently small proportion of followers are potential consumers.Finally,after taking consumers'knowledge about product features into account,the main results still hold,and when considering the competition between influencers,we uncover the conditions under which both influencers will choose to endorse the high-congruence product.
