Deep Learning Based Prediction Model for the Next Purchase

Utku, Anıl; Akçayol, M. Ali

doi:10.4316/aece.2020.02005

Cited by 11 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After this step, the optimal hyperparameters of original and proposed GS algorithm will be obtained. Performance of the original and proposed GS algorithms is evaluated using mean squared error (MSE) error loss defined as [27], [28]. (12) where [y1, y2, …, yn] and [𝑦 ̂1, 𝑦 ̂2, .…”

Section: Methods For Evaluatingmentioning

confidence: 99%

A new grid search algorithm based on XGBoost model for load forecasting

Ngoc¹,

Tran²,

Nguyen³

et al. 2023

Bulletin EEI

View full text Add to dashboard Cite

XGBoost is a highly effective and widely used machine learning model and its hyperparameters take an important role on the performance of the model. This paper presents a new grid search (GS) algorithm for obtaining optimal hyperparameters of the XGBoost model based on the median values of their error loss. A benchmark method used to evaluate the proposed and original GS algorithms is introduced. Datasets with measured daily electricity demand load values of Ho Chi Minh City, Vietnam and Tasmania state, Australia are analyzed for the performance of both algorithms. The error metrics, mean squared errors (MSEs), of the proposed algorithm are found to be 2,282 MW and 501 MW that are smaller than those of original algorithms, which are 2,424 MW and 537 MW in case of Ho Chi Minh City and Tasmania state, respectively. These results then verify the accuracy of the proposed algorithm.

show abstract

Section: Methods For Evaluatingmentioning

confidence: 99%

A new grid search algorithm based on XGBoost model for load forecasting

Ngoc¹,

Tran²,

Nguyen³

et al. 2023

Bulletin EEI

View full text Add to dashboard Cite

show abstract

“…There are many feature selection techniques to find the optimal subset of features from a given data in the literature. Some points are essential in deciding on a feature selection technique, such as contribution to the classifier's performance, reducing overfitting, or minimizing training time [20][21][22][23]. Metaheuristics have the potential to perform well in the feature selection process.…”

Section: Literature Reviewmentioning

confidence: 99%

A Hybrid Deep Learning-Metaheuristic Model for Diagnosis of Diabetic Retinopathy

Gürcan

Atıcı

Beyca

2023

Gazi University Journal of Science

View full text Add to dashboard Cite

International Diabetes Federation (IDF) reports that diabetes is one of the rapidly growing illnesses. About 463 million adults between 20-79 years have diabetes. There are also millions of undiagnosed patients. It is estimated that there will be about 578 million diabetics by 2030 [1]. Diabetes reasons different eye diseases. Diabetic retinopathy (DR) is one of them and is also one of the most common vision loss or blindness worldwide. DR progresses slowly and has few indicators in the early stages. It makes the diagnosis of DR a problematic task. Automated systems promise to support the diagnosis of DR. Many deep learning-based models have been developed for DR classification. This study aims to support ophthalmologists in the diagnosis process and increase the diagnosis performance of DR through a hybrid model. A publicly available Messidor-2 dataset was used in this study, comprised of retinal images. In the proposed model, first, images were pre-processed and a deep learning model, namely, InceptionV3 was used in feature extraction where a transfer learning approach is applied. Next, the number of features in obtained feature vectors was decreased with feature selection by Simulated Annealing (SA). Lastly, the best representation features were used in XGBoost model. The XGBoost algorithm gives an accuracy of 92.26% in a binary classification task. This study shows that a pre-trained ConvNet with a metaheuristic algorithm for feature selection gives a satisfactory result in the diagnosis of DR.

show abstract

“…The experimental results demonstrated successful segmentation of customers and building classifier to predict characteristics of unknown customers. Another study by [17] showed how data such as movie viewing, basket addition, and purchase in e-commerce can be used for the development of deep learning-based prediction model of the next purchase in e-commerce. The experimental results showed that the proposed model based on time series analysis is more successful in comparison with other models (random forest, Autoregressive Integrated Moving Average, Convolutional Neural Network, Multilayer Perceptron).…”

Section: Figure 6 Cluster Analysis Of Abstractmentioning

confidence: 99%

Visualising the Knowledge Domain of Artificial Intelligence in Marketing: A Bibliometric Analysis

Ismagiloiva¹,

Dwivedi²,

Rana³

2020

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

As the number of research outputs in the field of AI in Marketing increased greatly in the past 20 years, a systematic review of the literature and its developmental process is essential to provide a consolidated view of this area. This study conducted a bibliometric analysis for the knowledge domain of AI in Marketing by using 617 research outputs from the Web of Science database from 1992 to 2020. Knowledge maps of AI in marketing research were visualised by employing CiteSpace software.

show abstract

Deep Learning Based Prediction Model for the Next Purchase

Cited by 11 publications

References 20 publications

A new grid search algorithm based on XGBoost model for load forecasting

A new grid search algorithm based on XGBoost model for load forecasting

A Hybrid Deep Learning-Metaheuristic Model for Diagnosis of Diabetic Retinopathy

Visualising the Knowledge Domain of Artificial Intelligence in Marketing: A Bibliometric Analysis

Contact Info

Product

Resources

About