Time-varying hierarchical chains of salps with random weight networks for feature selection

Faris, Hossam; Heidari, Ali Asghar; Al-Zoubi, Ala’ M.; Mafarja, Majdi; Aljarah, Ibrahim; Eshtay, Mohammed; Mirjalili, Seyedali

doi:10.1016/j.eswa.2019.112898

“…[25] hybridised Grey Wolf Optimizer (GWO) with WOA for the FS problem. [1,[26][27][28] improved Salp Swarm Algorithm (SSA) for the FS problem. [15] used Social Spider Algorithm (SSA) for the FS problem.…”

Section: Related Workmentioning

confidence: 99%

Dynamic Butterfly Optimization Algorithm for Feature Selection

Tubishat

¹

,

Alswaitti

²

,

Mirjalili

³

et al. 2020

Self Cite

View full text Add to dashboard Cite

Feature selection represents an essential pre-processing step for a wide range of Machine Learning approaches. Datasets typically contain irrelevant features that may negatively affect the classifier performance. A feature selector can reduce the number of these features and maximise the classifier accuracy. This paper proposes a Dynamic Butterfly Optimization Algorithm (DBOA) as an improved variant to Butterfly Optimization Algorithm (BOA) for feature selection problems. BOA represents one of the most recently proposed optimisation algorithms. BOA has demonstrated its ability to solve different types of problems with competitive results compared to other optimisation algorithms. However, the original BOA algorithm has problems when optimising high-dimensional problems. Such issues include stagnation into local optima and lacking solutions diversity during the optimisation process. To alleviate these weaknesses of the original BOA, two significant improvements are introduced in the original BOA: the development of a Local Search Algorithm Based on Mutation (LSAM) operator to avoid local optima problem and the use of LSAM to improve BOA solutions diversity. To demonstrate the efficiency and superiority of the proposed DBOA algorithm, 20 benchmark datasets from the UCI repository are employed. The classification accuracy, the fitness values, the number of selected features, the statistical results, and convergence curves are reported for DBOA and its competing algorithms. These results demonstrate that DBOA significantly outperforms the comparative algorithms on the majority of the used performance metrics. INDEX TERMS Butterfly optimisation algorithm, feature selection, local search algorithm based on mutation.

show abstract

“…Due to small positive sample size and severe unbalance between positive and negative samples (1:45) in historical behavioral data in the dataset, the already known data one month before (November 18-December 18) the behavioral prediction date (December 19) could not be simply extracted as data samples, which formed the training set of the user purchasing behavioral prediction model. Given this, a "sliding window"-centroid under-sampling combined balance method was raised to construct training set and test set [5,24] .…”

Section: Sample Construction and Balancementioning

confidence: 99%

Application of Sample Balance-Based Multi-Perspective Feature Ensemble Learning for Prediction of User Purchasing Behaviors on Mobile Wireless Network Platforms

Zhang

¹

,

Dong

²

2020

Preprint

1

0

View full text Add to dashboard Cite

In recent years, with the rapid development of wireless communication network, M-Commerce has achieved great success. Relying on mobile phones, tablets and other wireless communication devices for online shopping has become a mainstream way for users to consume. Users leave a lot of historical behavior data when shopping on the M-Commerce platform. Using these data to predict future purchasing behaviors of the users will be of great significance for improving user experience and realizing mutual benefit and win-win result between merchant and user. Therefore, a sample balance-based multi-perspective feature ensemble learning was proposed in this study as the solution to predicting user purchasing behaviors, specifically including: 1) “Sliding window”-centroid under-sampling was combined with sample balance method was used, while the positive sample size was enlarged using “sliding window”, centroid under-sampling was used to reduce the negative sample size within “sliding window”, so as to acquire user’s historical purchasing behavioral data with sample balance. 2) Influence feature of user purchasing behaviors were extracted from three perspectives—user, commodity and interaction, in order to further enrich the feature dimensions. Meanwhile, feature selection was carried out using XGBSFS algorithm. 3) An ensemble learning model—five-fold cross validation stacking—which could be used to predict user purchasing behaviors was raised. Three prediction models—XGBoost-Logistics, LightGBM-L2 and cascaded deep forest models—so that they could realize mutual collaboration and the overall prediction ability of the ensemble learning model could be improved. 4) Large-scale real datasets were experimented on Alibaba M-Commerce platform. The experimental results show that the proposed method has achieved better prediction effect in various evaluation indexes such as precision and recall rate.

show abstract

“…Due to small positive sample size and severe unbalance between positive and negative samples (1:45) in historical behavioral data in the dataset, the already known data one month before (November 18-December 18) the behavioral prediction date (December 19) could not be simply extracted as data samples, which formed the training set of the user purchasing behavioral prediction model. Given this, a "sliding window"-centroid under-sampling combined balance method was raised to construct training set and test set [5,24]. User's historical behaviors were divided into: browse, collect, add to cart and purchase.…”

Section: Sample Construction and Balancementioning

confidence: 99%

Application of sample balance-based multi-perspective feature ensemble learning for prediction of user purchasing behaviors on mobile wireless network platforms

Zhang

¹

,

Dong

²

2020

Preprint

0

View full text Add to dashboard Cite

In recent years, with the rapid development of wireless communication network, M-Commerce has achieved great success. Relying on mobile phones, tablets and other wireless communication devices for online shopping has become a mainstream way for users to consume. Users leave a lot of historical behavior data when shopping on the M-Commerce platform. Using these data to predict future purchasing behaviors of the users will be of great significance for improving user experience and realizing mutual benefit and win-win result between merchant and user. Therefore, a sample balance-based multi-perspective feature ensemble learning was proposed in this study as the solution to predicting user purchasing behaviors, specifically including: 1) “Sliding window”-centroid under-sampling was combined with sample balance method was used, while the positive sample size was enlarged using “sliding window”, centroid under-sampling was used to reduce the negative sample size within “sliding window”, so as to acquire user’s historical purchasing behavioral data with sample balance. 2) Influence feature of user purchasing behaviors were extracted from three perspectives—user, commodity and interaction, in order to further enrich the feature dimensions. Meanwhile, feature selection was carried out using XGBSFS algorithm. 3) An ensemble learning model—five-fold cross validation stacking—which could be used to predict user purchasing behaviors was raised. Three prediction models—XGBoost-Logistics, LightGBM-L2 and cascaded deep forest models—so that they could realize mutual collaboration and the overall prediction ability of the ensemble learning model could be improved. 4) Large-scale real datasets were experimented on Alibaba M-Commerce platform. The experimental results show that the proposed method has achieved better prediction effect in various evaluation indexes such as precision and recall rate.

show abstract

Time-varying hierarchical chains of salps with random weight networks for feature selection

Cited by 83 publications

References 73 publications

Dynamic Butterfly Optimization Algorithm for Feature Selection

Dynamic Butterfly Optimization Algorithm for Feature Selection

Application of Sample Balance-Based Multi-Perspective Feature Ensemble Learning for Prediction of User Purchasing Behaviors on Mobile Wireless Network Platforms

Application of sample balance-based multi-perspective feature ensemble learning for prediction of user purchasing behaviors on mobile wireless network platforms

Contact Info

Product

Resources

About