Improving AdaBoost Classifier to Predict Enterprise Performance after COVID-19

Abstract

Because COVID-19 occurred in 2019, the behavioxr of humans has been changed and it will influence the business model of enterprise. Enterprise cannot predict its development according to past knowledge and experiment; so, it needs a new machine learning framework to predict enterprise performance. The goal of this research is to modify AdaBoost to reasonably predict the enterprise performance. In order to justify the usefulness of the proposed model, enterprise data will be collected and the proposed model can be used to predict the enterprise performance after COVID-19. The test data correct rate of the proposed model will be compared with some of the traditional machine learning models. Compared with the traditional AdaBoost, back propagation neural network (BPNN), regression classifier, support vector machine (SVM) and support vector regression (SVR), the proposed method possesses the better classification ability (average correct rate of the proposed method is 88.04%) in handling two classification problems. Compared with traditional AdaBoost, one-against-all SVM, one-against-one SVM, one-against-all SVR and one-against-one SVR, the classification ability of the proposed method is also relatively better for coping with the multi-class classification problem. Finally, some conclusions and future research will be discussed at the end.

Sentiment Informed Sentence BERT-Ensemble Algorithm for Depression Detection

“…AdaBoost (Adaptive Boosting) is an ensemble learning algorithm that combines the predictions of multiple weak classifiers to create a strong classifier. It works by focusing on the training samples that are hard to classify and adjusting the weights of the weak classifiers accordingly [58].…”

Visualizing the historical COVID-19 shock in the US airline industry: A Data Mining approach for dynamic market surveillance

“…A couple of works that have tackled the practical application of ML algorithms during the pandemics are ( Pérez-Campuzano et al, 2021a ), which gathers and proposes a handful of strategic AI applications that could be implemented during these times of crisis, and ( Tsa and Hung, 2021 ), where a model is modified to predict enterprise performance and compared against different engines such as Neural Networks.…”

A Computerized Doughty Predictor Framework for Corona Virus Disease: Combined Deep Learning based Approach

“…The proposed method utilizes the concept of the Adaptive Boosting process to fuse the decisions which is a weighted and iterative method. The classification ability of the Ada Boost method is significantly higher than other learners [48] since at every iteration it concentrates on more complex samples by reducing the weight of correctly classified samples and increase the probability of selecting the misclassified samples. Likewise, Ada Boost Doughty Learners (ABDL) concentrates on handling the more informative and complex samples by making subsequent learners correct the mistakes of its predecessor.…”