The role of big data and IoT in logistics supply chain management of e-commerce

Abstract

With the rapid development of social mode virtualization and electronic component technology, the application of data science and Internet of Things (IoT) technology in the field of e-commerce is gradually increasing. This study aims to explore how these emerging technologies can enhance the advantage of Chinese e-commerce companies in international competition. By comprehensively analyzing the massive data generated by online social networking and the application of IoT sensor technology in logistics and enterprise management, this paper proposes a decision support model based on data analysis. Research methods include data collection, data analysis and case studies. The results of the study show that data analytics and IoT technologies can effectively improve the efficiency of e-commerce operations and customer experience. The conclusion is that these technologies not only contribute to the domestic development of e-commerce enterprises, but also play a non-negligible role in international competition. This research has important implications for understanding the practical applications and potential of new technologies in the field of e-commerce.

Keywords

Electronic commerce Internet of Things big data supply chain management decision support model

1. Introduction

1.1 Research needs and objectives

With the increasing importance of e-commerce in the modern economy, the demand for logistics and supply chains has also increased dramatically. However, research on how to leverage big data and IoT technologies to optimize e-commerce logistics and supply chain management is relatively scarce. Most of the existing research focuses on the single application of big data and IoT, while there is a lack of clear and comprehensive understanding of the integrated application of the two in e-commerce logistics and supply chain management.

In the context of the rapid development of e-commerce and Internet of Things (IoT), the role of big data technology in e-commerce logistics supply chain management has been paid more and more attention. Alrumiah and Hadwan highlighted the key role of big data analytics in e-commerce from both supplier and customer perspectives, particularly in optimizing business decisions and improving operational efficiency [1]. This view is further confirmed by Oncioiu et al., whose research shows that big data analysis can significantly improve the company performance of supply chain management [2]. The Internet of Things (IoT) also plays an important role in the supply chain management of e-commerce. Misra et al. proposed that IoT has great potential for supply chain performance in the agriculture and food industries when combined with big data and artificial intelligence [3]. In addition, Liu and Zheng pointed out that 5G technology provides a broader application scenario for IoT, especially in supply chain logistics management [4]. More and more research has also begun to focus on supply chain optimization and management. For example, Zhou and Liu found that blockchain can improve transparency and efficiency in cross-border e-commerce supply chain management [5]. Gopal et al. further proved that big data analysis can significantly improve supply chain performance [6]. Most notably, more and more research is beginning to focus on the integrated application of big data and IoT in e-commerce logistics supply chain management. A case study by Hopkins and Hawking specifically stated that the combined use of big data analytics and IoT can deliver greater operational efficiency and a better customer experience in logistics [7]. In summary, big data and the Internet of Things in e-commerce logistics supply chain management can not only optimize the supply chain, improve operational efficiency, but also provide a better customer experience. These studies not only provide a solid theoretical foundation for the application of big data and IoT in this field, but also point to valuable directions for future empirical research.

Therefore, this study aims to solve the core problem of how to effectively integrate big data and IoT into e-commerce logistics supply chain management, including but not limited to demand forecasting, real-time tracking, inventory management, etc. Through empirical analysis and case studies, we hope to find and propose a set of effective strategies and models to provide specific application guidance for e-commerce logistics supply chain management. In addition, this study may provide a theoretical and practical basis for future research in this field.

1.2 Big data

Big data refers to software programs that conduct high-speed analysis of large and complex data sets to reveal useful information [8]. It is playing an increasingly important role in today’s world, especially in the field of e-commerce and logistics. The core objective of this study is to explore how big data, combined with “Internet $+$ ” technology, can promote the transformation of logistics industry from traditional mode to intelligent mode [9, 10, 11, 12].

In the era of information explosion, big data provides the ability to analyze massive data in the shortest possible time to mine valuable information [13]. This analytical ability is especially applicable to e-commerce logistics supply chain management, helping enterprises to make more accurate demand prediction, real-time logistics tracking, and more efficient resource allocation [14, 15, 16]. For example, in e-commerce transactions, big data enables personalized recommendations, while also optimizing inventory and delivery through predictions of purchase behavior.

China has established a number of big data industrial parks, and many cities have dedicated big data management agencies, indicating that the country and enterprises have recognized the importance of big data in future development.

In general, big data is not only a technological trend [17], but also a key tool for self-transformation and optimization in the e-commerce and logistics industries.

1.3 The Internet of Things

Since the beginning of the 21st century, the Internet of Things (IoT) has not only become one of the most well-known new technologies in the telecom industry, but also is considered to be a key technology that can open up huge growth space for the telecom industry in the future [18, 19, 20, 21, 22]. By connecting devices, data and users, the Internet of Things provides operators and enterprises with diversified business models and services, thereby increasing their market competitiveness.

As operators gradually incorporate IoT into their long-term development strategies, we are seeing the overall construction of IoT networks on a global scale. These networks not only support traditional device interconnection, but also promote the rapid development of emerging application scenarios, such as smart home, industrial automation, and medical and health fields [23, 24, 25, 26]. These applications not only enrich the application level of the Internet of Things, but also bring unprecedented opportunities and challenges to the telecommunications industry. The specific situation is shown in Fig. 1.

Figure 1.

The development trend of IoT technology.

The Internet of Things represents a new stage of information development, achieving a high degree of interconnection between people, people and things, and things and things. This connected way is widely used in many fields such as industrial automation, smart home, medical health and intelligent transportation. While there is no single unit of measurement, the performance and scale of iot is often assessed through multiple dimensions such as number of devices, data transfer rate (bps), transmission delay (ms), coverage (m or km), and energy efficiency (W). These indicators change according to application scenarios and needs, reflecting the diversity and complexity of the Internet of Things.

Overall, the application of the Internet of Things in the telecommunications industry has expanded from a single device connection to a comprehensive digital ecosystem construction, and its impact has also penetrated into the business model and market layout from the technical level. Therefore, a deep understanding and application of IoT technology will be one of the key factors for the continued growth of the telecom industry in the future.

1.4 Enterprise role allocation

Supply chain not only covers the whole process from raw materials and supplies to production, products and customer orders [27, 28, 29], but also includes a multi-level enterprise network that provides products or services to end users [30]. In this network, enterprises of different sizes and different product types have their unique roles and positions. In this article, we will focus on how big data and the Internet of Things (IoT) are impacting and optimizing the role configuration of these enterprises in supply chain management. In particular, we will examine how big data can provide more accurate demand forecasting and how IoT can track and optimize logistics processes in real time, thereby improving the efficiency and responsiveness of the supply chain as a whole.

2. Questionnaire survey and analysis

In order to investigate the status quo of this area of China’s enterprises involved, the author distributed an online questionnaire developed by the Questionnaire Star platform to 50 heads of logistics departments and 50 technical employees of 25 large-scale e-commerce enterprises. For issues such as enterprise logistics supply chain management, training and recruitment of technical talents, current supply chain management decision-making, and logistics information transparency, 100 questionnaires were distributed, 100 were recovered, and the recovery rate was 100%. In order to sort out the logistics doctoral degree talents of e-commerce enterprises, this paper selects 5 of the most typical e-commerce enterprises to display the questionnaire data after processing the questionnaire. The data analysis unit of this study is individual respondents. We used SPSS software for statistical analysis of data, including descriptive statistics, Chi-square test and correlation analysis. The training situation of logistics supply chain management talents is shown in Table 1.

Table 1
PSNR results [dB] and $\delta$ values of various test images

Num	Possess a doctorate degree in logistics	Possess big data talents	Possess Internet of Things talents
1	1/25	3/25	2/25
2	2/25	4/25	4/25
3	1/25	2/25	5/25
4	3/25	1/25	3/25
5	0/25	3/25	3/25

As shown in Table 1, we find that logistics supply chain management talent training is still a weak link in most enterprises. It can be seen from Table 2 that the probability of decision-making mistakes in the enterprises surveyed is more than 25%. In addition, most of the five e-commerce companies in the list have no auxiliary tools for their logistics and supply chain decisions, and rely on the leadership team to make decisions, so the accuracy of their decisions cannot be judged. Through questionnaire survey, we can have a basic understanding of the current situation, but the validity and reliability of questionnaire survey can only be found in the actual test. Based on the theoretical analysis of the reliability and validity of the questionnaire, the correlation coefficient of the questionnaire is shown in Table 2.

It can be found that there is still much room for improvement in the work of the respondents in this field. Most enterprises even have less than 30% transparency, and the incidence of logistics information breakpoints is as high as 70%. It can be said that the backwardness in this field has seriously affected the development of relevant Chinese enterprises.

Table 2

Reliability and validity analysis

	Reliability	Validity
Value	Alpha $=$ 0.81	KMO $=$ 0.86

In Table 2, the results show that the probability of decision-making error of the surveyed enterprises is greater than 25%. This is largely because most companies lack effective AIDS in the decision-making process and rely heavily on the experience of the leadership team to make decisions.

To verify the reliability and validity of the questionnaire, Cronbach’s Alpha and KMO tests were conducted in this study. The results showed that Cronbach’s Alpha value was 0.81 and KMO value was 0.86, both exceeding the accepted standards, indicating that this study had high reliability and validity.

In order to conduct a more comprehensive analysis of the data collected by the questionnaire, in addition to traditional statistical methods, this paper also adopts machine learning algorithms, especially for evaluating the application of machine learning in logistics supply chain management. The main formulas and models involved are as follows:

(1)

The exponential distribution model is used to evaluate the probability of event occurrence, as shown in Eq. (1) below:

$\displaystyle P({x\leqslant x_{0}})=1-e^{-x_{0}/\mu}$ (1)

(2)

Optimization model of supply chain management, as shown in Eq. (2) below:

$\displaystyle{M}_{0}={U}-\frac{\Delta_{2}}{\Delta_{1}+\Delta_{2}}\times i$ (2)

(3)

Logistic regression model is used to evaluate the impact of various factors (such as technology, management team, etc.) on the accuracy of logistics decision-making, as shown in Eq. (3) below:

$\displaystyle\ln\left({\frac{p}{1-p}}\right)=\beta_{0}+\beta_{1}x_{1}+\beta_{2% }x_{2}+\ldots+\beta_{n}x_{n}$ (3)

(4)

The random forest algorithm is used to evaluate the importance and effectiveness of machine learning in logistics supply chain management.

After comprehensive analysis of statistical algorithms, it can be found that the utilization rate and importance of machine learning technology are the highest among the companies currently surveyed.

3. Analysis of the problems existing in the current e-commerce logistics supply chain management

3.1 Insufficient technical talent pool

Comprehensive analysis, based on questionnaires and big data algorithms, reveals a fact that cannot be ignored: most companies involved in e-commerce logistics supply chain management are facing a shortage of professional and technical personnel. Of the 25 companies surveyed, the vast majority reported a lack of talent with IT and iot expertise. Further, when it comes to emerging technology fields, such as artificial intelligence and blockchain, this talent shortage is even more pronounced. To stay ahead of the global e-commerce competition, these companies need to urgently address the skills shortage.

3.2 Logistics supply chain management decision without data support

Despite the changing market environment and complex supply chain management challenges, most companies still rely too much on the experience and subjective judgment of the management team to make decisions. This not only increases the risk of decision-making errors, but also exposes weaknesses in supply chain management systems that lack scientific and data support. It is particularly noteworthy that although advanced analytical tools such as big data and machine learning have been successfully applied in other fields, their application in e-commerce logistics supply chain management is still relatively lagging behind.

3.3 The logistics supply chain information is not transparent

In the process of data analysis, another prominent problem is the opacity of supply chain information. For example, the ability to track goods in real time is compromised once they are out of storage or delivered. RFID and other iot technologies can solve this problem to some extent, but they require special hardware devices to read and upload information, which causes the flow of information to break down across multiple nodes. This situation not only has an impact on internal operations, but also may cause customers to lose confidence due to the lack of timely and accurate logistics information.

4. Some suggestions for optimizing the management model

4.1 Strengthen the training and recruitment of new technology talents

In order to solve the shortage of technical talents in e-commerce logistics supply chain management, a multi-angle strategy is necessary. First, companies can partner with higher education institutions to offer specialized courses directly related to logistics and supply chain management in these schools. These customized educational programs can be designed according to the specific needs of the company, ensuring that students can directly adapt to the corporate environment and immediately enter the professional work after graduation.

In addition, in terms of internal talent training, enterprises should also carry out continuous vocational training for existing contract employees. This can not only enhance the professional competence of employees, but also help to form a more complete and diversified technical talent pool.

Finally, through social recruitment channels, companies should actively attract and introduce talents with advanced technical capabilities, especially in emerging technologies such as the Internet of Things, blockchain and artificial intelligence. For example, bringing in people who understand blockchain technology can greatly improve the accuracy and security of logistics information tracking.

Figure 2 further reveals the obvious improvement and increase in the reserves of technical talents after the implementation of this comprehensive talent strategy.

Figure 2.

Changes in talent reserve of enterprises after adopting the new strategy.

4.2 Provide data support for logistics supply chain management decision-making through big data technology

It can be seen from Fig. 3 that the supply chain decision accuracy of enterprises using big data technology is higher than that of enterprises without big data technology. And in each cycle test, compared with the two, the research shows that the accuracy of using big data technology is about 0.2 $\sim$ 0.3 higher than that without using big data on average. It can be concluded that enterprises using big data technology have higher accuracy in supply chain decision-making.

Figure 3.

Changes in the accuracy of enterprise supply chain decision-making after adopting big data technology.

The continuous progress of information science provides the excellent development opportunities for some enterprises. The unstructured database of the logistics supply chain of commercial enterprises provides data support for big data technical analysis, and then allows the leadership team of the e-commerce enterprise to write the analysis logic of daily decision-making into a document and deliver it to the IT development part of the e-commerce enterprise, and ask the IT development to integrate the daily logistics. Supply chain decision-making is developed into a program that can be automatically analyzed. Ultimately, the logistics supply chain management can make company combine a lot of important information and the different opinions of human members of the leadership team to form the final decision-making content, thereby improving the accuracy of logistics supply chain decision-making. Reduce the occurrence of human error. Figure 3 shows the changes in the accuracy of enterprise supply chain decision-making after adopting big data technology.

Figure 4.

Using RFID and RUBee for logistics supply chain management, the probability comparison of opaque information.

Figure 5.

Information transparency of logistics supply chain corresponding to RFID and RUBee technology.

4.3 Improve the transparency of logistics supply chain information through IoT technology

Although RFID technology has played a role in logistics supply chain management, its limitations – such as information breakpoints and data incompleteness – have become increasingly prominent. Fortunately, other communication technologies in the Internet of Things (IoT) offer more advanced and comprehensive solutions to this problem. Taking RUBee technology as an example, its excellent anti-interference ability enables it to provide a more stable and coherent information flow in the logistics process, thus eliminating the phenomenon of information breakpoints.

Figure 4 shows a comparison of information transparency in logistics supply chain management using traditional RFID versus RUBee technology. From this comparison, we can clearly see that RUBee technology has significant advantages in improving information transparency.

By implementing RUBee or similar advanced iot technologies, e-commerce companies are not only able to track information throughout the supply chain, but are also more likely to win the trust of customers and increase their loyalty. Figure 5 further details how iot technologies such as RFID and RUBee contribute to increased transparency in logistics supply chains.

5. Conclusions

Driven by big data and the Internet of Things, the number of companies involved in this field is gradually increasing. For these companies, efficient management and advanced technology are key to gaining customer trust. Therefore, more funds and resources will be invested in the introduction of Internet of Things and big data technology to support the continued operation of e-commerce enterprises. Through detailed description and analysis of related concepts, as well as questionnaire survey and big data analysis of relevant domestic enterprises, this paper finds the main problems in the current industry, such as the shortage of technical talents, the lack of data support for decision-making, and the lack of transparency of logistics information.

In response to these problems, the paper suggests strengthening the training and recruitment of new technical personnel, as well as the wider application of big data in logistics and supply chain management. The Internet of Things technology can not only provide strong data support for decision-making, but also greatly improve the transparency of logistics and supply chain information, thus solving a variety of problems existing in the current industry.

Future outlook: With the continuous maturity and wide application of the Internet of Things and big data technologies, we foresee a more efficient, transparent and intelligent supply chain management model will gradually take shape. In addition, with the introduction of advanced technologies such as artificial intelligence and machine learning, we can expect supply chain management to be more personalized and automated in the near future, which will further enhance the competitiveness of enterprises and customer satisfaction.

Footnotes

Acknowledgments

This research was supported by National Social Science Fund 22BJY013 Research on the Mode Selection and Implementation Path of the Construction of a Unified Domestic Market under the Background of a Trade Power; 21YJA790046, Humanities and Social Sciences Project of the Ministry of Education, “Research on the Construction and Implementation Path of Modern Circulation System for Rural Comprehensive Revitalization”.

References

Alrumiah

Hadwan

. Implementing big data analytics in e-commerce: vendor and customer view. IEEE Access. 2021; 9: 37281-37286.

Oncioiu

Bunget

Türkeş

Căpuşneanu

Topor

Tamaş

, et al. The impact of big data analytics on company performance in supply chain management. Sustainability. 2019; 11: 4864.

Misra

Dixit

Al-Mallahi

Bhullar

Upadhyay

Martynenko

. IoT, big data, and artificial intelligence in agriculture and food industry. IEEE Internet Things. 2022; 9(9): 6305-6324.

Liu

Zheng

. Intelligent management of supply chain logistics based on 5g LoT. Cluster Comput. 2022; 25(3): 2271-2280.

Zhou

Liu

. Blockchain-enabled cross-border e-commerce supply chain management: A bibliometric systematic review. Sustainability. 2022; 14: 15918.

Gopal

PRC

Rana

Krishna

Ramkumar

. Impact of big data analytics on supply chain performance: an analysis of influencing factors. Ann Oper Res. 2022. doi: 10.1007/s10479-022-04749-6.

Hopkins

Hawking

. Big data analytics and IoT in logistics: A case study. Int J Logist Manag. 2018; 29(2): 575-591.

Wang

Shen

Zhao

. Understanding the role of big data analytics for coordination of electronic retail service supply chain. J Enterp Inf Manag. 2022; 35(4/5): 1392-1408.

Zhao

Zhou

Deng

. Innovation mode and optimization strategy of B2C e-commerce logistics distribution under big data. Sustainability. 2020; 12: 3381.

10.

Tao

Wang

Rocchio

. Big data driven agricultural products supply chain management: A trustworthy scheduling optimization approach. IEEE Access. 2018; 6: 49990-50002.

11.

Kalkha

Khiat

Bahnasse

Ouajji

. The rising trends of smart e-commerce logistics. IEEE Access. 2023; 11: 33839-33857.

12.

Golinska-Dawson

Werner-Lewandowska

Kolinska

Kolinski

. Impact of market drivers on the digital maturity of logistics processes in a supply chain. Sustainability. 2023; 15: 3120.

13.

Lamba

Yadav

Barve

Panda

. Prioritizing barriers in reverse logistics of E-commerce supply chain using fuzzy-analytic hierarchy process. Electron Commer Res. 2020; 20(2): 381-403.

14.

Guo

Gao

Wang

. Share or not share: the optimal logistics service strategy in a dual-channel e-commerce supply chain. Electron Commer Res. 2022. doi: 10.1007/s10660-022-09613-0.

15.

Lahkani

Wang

Urbański

Egorova

. Sustainable B2B e-commerce and blockchain-based supply chain finance. Sustainability. 2020; 12: 3968.

16.

Liu

Wang

Zhu

Wang

Shen

. Order allocation of logistics service supply chain with fairness concern and demand updating: Model analysis and empirical examination. Ann Oper Res. 2018; 268(1-2): 177-213.

17.

Xue

. Cost optimization control of logistics service supply chain based on cloud genetic algorithm. Wireless Pers Commun. 2018; 102(4): 3171-3186.

18.

Chi

Hao

. Customer demand analysis of the electronic commerce supply chain using Big Data. Ann Oper Res. 2018; 268(1-2): 113-128.

19.

Hosseini-Motlagh

Johari

Nematollahi

Pazari

. Reverse supply chain management with dual channel and collection disruptions: Supply chain coordination and game theory approaches. Ann Oper Res. 2023; 324(1-2): 215-248.

20.

Han

Chen

Luo

Foropon

CRH

Belal

. A multi-period closed-loop supply chain network design with circular route planning. Ann Oper Res. 2022. doi: 10.1007/s10479-022-04848-4.

21.

Prakash

Kumar

Soni

. Jain

Rathore

APS

. Closed-loop supply chain network design and modelling under risks and demand uncertainty: An integrated robust optimization approach. Ann Oper Res. 2020; 290(1-2): 837-864.

22.

Chen

Yang

. Research to key success factors of intelligent logistics based on IoT technology. J Supercomput. 2022; 78(3): 3905-3939.

23.

Jiang

Chen

Wang

. Fast artificial bee colony algorithm with complex network and naive bayes classifier for supply chain network management. Soft Comput. 2019; 23(24): 13321-13337.

24.

Zhu

. Application of RBF network structure and data mining in e-commerce network marketing. Soft Comput. 2023. doi: 10.1007/s00500-023-08791-9.

25.

Deng

Shi

Wang

Gaur

. Testing the adoption of Blockchain technology in supply chain management among MSMEs in China. Ann Oper Res. 2022. doi: 10.1007/s10479-022-04856-4.

26.

Roy

Pamučar

Kar

. Evaluation and selection of third party logistics provider under sustainability perspectives: An interval valued fuzzy-rough approach. Ann Oper Res. 2020; 293(2): 669-714.

27.

Zhang

Qiu

. An intelligent cloud computing of trunk logistics alliance based on blockchain and big data. J Supercomput. 2021; 77(12): 13863-13878.

28.

Yang

Guo

Sun

Zhang

. Contextual and organizational factors in sustainable supply chain decision making: Grey relational analysis and interpretative structural modeling. Environ Dev Sustain. 2021; 23(8): 12056-12076.

29.

Chung

Weaver

Jeon

. Sustainable management of remanufacturing in dynamic supply chains. Netw Spat Econ. 2020; 20(3): 703-731.

30.

Zhang

Fan

Tian

. Optimal operational strategies of capital-constrained supply chain with logistics service and price dependent demand under 3PL financing service. Soft Comput. 2020; 24(4): 2793-2806.

The role of big data and IoT in logistics supply chain management of e-commerce

Abstract

Keywords

1. Introduction

1.1 Research needs and objectives

1.2 Big data

1.3 The Internet of Things

2. Questionnaire survey and analysis

Table 1 PSNR results [dB] and δ values of various test images

3.1 Insufficient technical talent pool

3.2 Logistics supply chain management decision without data support

3.3 The logistics supply chain information is not transparent

4. Some suggestions for optimizing the management model

4.1 Strengthen the training and recruitment of new technology talents

5. Conclusions

Footnotes

Acknowledgments

References

Table 1
PSNR results [dB] and $\delta$ values of various test images