The automotive industry is the leading producer of machines in Taiwan and worldwide. Developing effective methods for forecasting car sales can allow car companies to arrange their production and sales plans. Capitalizing on the growth of social media and deep learning algorithms, this research aimed to improve the overall performance of the forecasting of Taiwan car sales movement direction forecasting by using online sentiment data and CNN-LSTM method. First, the historical sales volumes and multi-channel online sentiment data for six car brands in Taiwan were collected and preprocessed for labeling of car sales movement direction. Then, three models, namely, the classical, sentimental, and CNN-LSTM models, were constructed and trained/fitted for forecasting car sales movement directions in Taiwan. Finally, the performance of the three prediction models were compared to verify the effects of online sentiment data and the CNN-LSTM model on forecasting performance. The results showed that four forecasting performance indices, i.e., accuracy, precision, recall and F1-score, improved by 27.78% (from 41.67% to 69.45%), 0.39 (from 0.38 to 0.77), 0.27 (from 0.42 to 0.69) and 0.33 (from 0.35 to 0.68), respectively. Therefore, the online sentiment data and CNN-LSTM method can indeed improve the overall performance of car sales movement direction in Taiwan.

Purpose: The purpose of this paper is to conceptualize how information technology (IT) enables supply chain (SC) network capabilities, which is to capitalize on SC’s existing set of resources and, at the same time, manage new combinations of SC resources to meet future market needs. The paper also develops SCM framework associated with IT-enabled SC network capabilities.Design/methodology/approach: Through a case study of a leading Taiwanese petrochemical corporation, qualitative data were gathered on the IT-related SC management practices, in terms of network resource mobilizing and adaptive co-management arrangements to enable SC network capability. This research is based primarily on the interviews of the case company, supplemented by archived documents, published books, and in-depth observations.Findings: Based on the evidence from the case, this study inductively develops a model that includes the operating processes with IT-enabled activities to achieve ambidextrous SC network capability, and the relevant framework functions in network resources and co-management activities include information co-governance, information interoperability, community engagement strategy, cyber-physical dexterity, and control enactment, which lead the SC alliances improvements for dynamic environmental changes.Practical implications: Practitioners may derive strategies and tactics from the current findings to help them implement innovative information technologies and setup SC framework, during SC network capability development, to achieve SC’s sustainable competence in a dynamic market.Originality/value: Researchers and practitioners may obtain a more complete view of IT-enabled SC network capability development. The proposed model reveals that developing IT-enabled SC network capabilities is a dynamic process whereby an organization’s major SC managerial activities are divided into specific network resource mobilizing and adaptive co-management arrangements.

The hierarchical facility location problem (HFLP) is defined as determining the location of facilities in such a way that high-level facilities can serve the facilities in low-level efficiently. In this paper, a mixed integer programming model for the HFLP with the flow capacity constraint is proposed. An approach hybrided PSO and Tabu search (TS) (HPSO-TS) is proposed to solve the HFLP. The objective is to minimize overall demand-weighted distance travel, facility operating costs, and flow assignment costs. This method transforms PSO particles representing various dimensions of the attributes into a Tabu priority list and then constructs the assignment networks. The performance of the proposed algorithm is compared with branch-and-bound algorithm, a genetic algorithm, and classical PSO. Numerical results show that the performance of the proposed algorithm is better than those with exact methods when solving such problems. Finally, the proposed algorithm is applied to solve a case company in Jakarta.

Process mining (PM) is a technique to extract a process model from an event log to represent the process behaviour recorded in that event log. A mined process model with high fitness means that it can reflect most of the process behaviour recorded in the event log. Previous studies have shown that the mined model with high fitness can be used in process improvement, such as fraud detection, continuous process improvement and benchmarking. Genetic process mining (GPM) is a famous PM approach, which can simultaneously identify several process structures from event logs. However, GPM cannot effectively discover parallel structures from event logs. This study proposes a PM approach based on integration of GPM, particle swarm optimisation and differential evolution to find process models with high fitness for event logs involving multiple parallel structures. The results show that the proposed approach does indeed lead to improvement in gaining process models with high fitness for event logs involving multiple parallel structures.