Capturing Temporal Dynamics of Users’ Preferences from Purchase History Big Data for Recommendation System

Li, Chen; He, Minjia; Qaosar, Mahboob; Ahmed, Saleh; Morimoto, Yasuhiko

doi:10.1109/bigdata.2018.8622411

“…There are also some studies about route planning. A series of data such as the information released by users on social media, shopping search records and historical travel trajectories can be analyzed to give a weight in line with driver’s preference [ 28 , 29 , 30 , 31 , 32 , 33 ].…”

Section: Problem Description and Formulationmentioning

confidence: 99%

Personalized Route Planning System Based on Driver Preference

Wang

¹

,

Zhou

²

,

Gao

³

et al. 2021

Sensors

View full text Add to dashboard Cite

At present, most popular route navigation systems only use a few sensed or measured attributes to recommend a route. Yet the optimal route considered by drivers needs be based on multiple objectives and multiple attributes. As a result, these existing systems based on a single or few attributes may fail to meet such drivers’ needs. This work proposes a driver preference-based route planning (DPRP) model. It can recommend an optimal route by considering driver preference. We collect drivers’ preferences, and then provide a set of routes for their choice when they need. Next, we present an integrated algorithm to solve DPRP, which speeds up the search process for recommending the best routes. Its computation cost can be reduced by simplifying a road network and removing invalid sub-routes. Experimental results demonstrate its effectiveness.

show abstract

“…These challenges have prompted researchers to seek more efficient and innovative approaches to accelerate the drug development process [3,4]. In recent years, deep learning has been widely used in stock price prediction [5], software reliability [6], recommendation systems [7][8][9], and medical systems [10,11]. The development of deep learning provides effective solutions to drug generation research challenges [12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Quantitative evaluation of molecular generation performance of graph-based GANs

Zhang,

Wang,

Jiang

et al. 2024

Software Qual J

Self Cite

1

0

View full text Add to dashboard Cite

Deep generative models have been widely used in molecular generation tasks because they can save time and cost in drug development compared with traditional methods. Previous studies based on generative adversarial network (GAN) models typically employ reinforcement learning (RL) to constrain chemical properties, resulting in efficient and novel molecules. However, such models have poor performance in generating molecules due to instability in training. Therefore, quantitative evaluation of existing molecular generation models, especially GAN models, is necessary. This study aims to evaluate the performance of discrete GAN models using RL in molecular generation tasks and explore the impact of different factors on model performance. Through evaluation experiments on QM9 and ZINC datasets, the results show that noise sampling distributions, training epochs, and training data volumes can affect the performance of molecular generation. Finally, we provide strategies for stable training and improved performance for GAN models.

show abstract

“…These challenges have prompted researchers to seek more efficient and innovative approaches to accelerate the drug development process [3,4]. In recent years, deep learning has been widely used in stock price prediction [5], software reliability [6], recommendation systems [7][8][9], and medical systems [10,11]. The development of deep learning provides effective solutions to drug generation research challenges [12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Quantitative Evaluation of Molecular Generation Performance of Graph-based GANs

Zhang,

Wang,

Jiang

et al. 2023

Preprint

Self Cite

1

0

View full text Add to dashboard Cite

Deep generative models have been widely used in molecular generation tasks because they can save time and cost in drug development compared with traditional methods. Previous studies based on generative adversarial network (GAN) models typically employ reinforcement learning (RL) to constrain chemical properties, resulting in efficient and novel molecules. However, such models have poor performance in generating molecules due to instability in training. Therefore, quantitative evaluation of existing molecular generation models, especially GAN models, is necessary. This study aims to evaluate the performance of discrete GAN models using RL in molecular generation tasks and explore the impact of different factors on model performance. Through evaluation experiments on QM9 and ZINC datasets, the results show that noise sampling distributions, training epochs, and training data volumes can affect the performance of molecular generation. Finally, we provide strategies for stable training and improved performance for GAN models.

show abstract

Capturing Temporal Dynamics of Users’ Preferences from Purchase History Big Data for Recommendation System

Cited by 10 publications

References 9 publications

Personalized Route Planning System Based on Driver Preference

Personalized Route Planning System Based on Driver Preference

Quantitative evaluation of molecular generation performance of graph-based GANs

Quantitative Evaluation of Molecular Generation Performance of Graph-based GANs

Contact Info

Product

Resources

About