Professional Documents
Culture Documents
Survey
Survey
Abstract—Efficient matching between carriers and shippers harnessing the power of advanced technologies like machine
is crucial in the logistics industry to optimize resource learning, we can address longstanding challenges in carrier-
utilization and minimize costs. In this paper, we propose a shipper matching and pave the way for more efficient and
smart recommendation system based on multilabel sustainable logistics practices.
classification techniques to enhance the carrier-shipper
matching process. The system leverages machine learning
algorithms to predict multiple relevant carrier options for a II. LITERATURE REVIEW
given shipment request. We present a comprehensive literature
review on related works in carrier-shipper matching and The literature on carrier-shipper matching encompasses a
multilabel classification methodologies. Our proposed system wide range of approaches, including heuristic algorithms,
offers significant improvements over traditional methods by optimization models, and machine learning techniques.
considering multiple factors simultaneously, resulting in more Heuristic algorithms, such as nearest neighbor methods or
accurate and personalized recommendations. Experimental greedy algorithms, offer simplicity and computational
results demonstrate the effectiveness and feasibility of the
efficiency but may struggle to handle complex logistics
proposed approach in enhancing the efficiency and
effectiveness of carrier-shipper matching processes.
scenarios effectively.
Optimization models formulate carrier-shipper matching
Keywords— Carrier-Shipper Matching, Multilabel as a mathematical optimization problem, seeking to find the
Classification, Recommendation System, Logistics, Machine best solution based on predefined objectives and constraints.
Learning While optimization models can theoretically yield optimal
solutions, they often face challenges related to scalability,
I. INTRODUCTION computational complexity, and the need for accurate input
data.
The logistics industry is a critical component of global Machine learning techniques, particularly multilabel
commerce, facilitating the movement of goods from classification, have emerged as a promising approach to
manufacturers to consumers efficiently and reliably. Central carrier-shipper matching. Multilabel classification allows for
to the success of logistics operations is the effective the prediction of multiple labels or classes for a given input
matching of carriers with shippers, a process that influences instance, making it well-suited for the multifaceted nature of
resource utilization, transportation costs, and customer the matching problem in logistics.
satisfaction. However, traditional methods of carrier-shipper
matching often rely on manual processes or simplistic Recent studies have demonstrated the effectiveness of
algorithms, leading to suboptimal outcomes in an multilabel classification in various recommendation tasks,
increasingly complex and dynamic environment. such as product recommendation, movie recommendation,
and job recommendation. However, there is limited research
In this paper, we propose a smart recommendation on applying multilabel classification to carrier-shipper
system for carrier-shipper matching using multilabel matching in the logistics domain, presenting an opportunity
classification techniques. By leveraging machine learning for further exploration and innovation. By going through
algorithms, we aim to enhance the efficiency and accuracy of various reviews and machine learning models we found that
the matching process, ultimately improving supply chain the issue can be viewed based on criteria based selections
performance and customer service levels. Our approach and with the help of previous data.
considers multiple factors simultaneously, such as carrier
capacity, availability, route compatibility, and service
III. SELECTION OF RESEARCH PROBLEM
quality, to provide personalized and data-driven
recommendations for each shipment request. Efficient carrier-shipper matching is critical for
optimizing logistics operations, minimizing costs, and
The significance of our research lies in its potential to ensuring timely delivery of goods. However, traditional
revolutionize logistics operations, driving cost savings, methods of matching often fall short in meeting the demands
improving resource utilization, and enhancing the overall of the modern logistics landscape. These methods typically
competitiveness of businesses in the supply chain. By
X. CONCLUSION
In conclusion, this survey paper has provided a
comprehensive examination of smart recommendation REFERENCES
systems for carrier-shipper matching using multilabel
classification. Through an in-depth analysis of [1] Hybrid XGBoost-SVM Model for Multi-criteria Carrier Selection in
methodologies, algorithms, datasets, evaluation metrics, E-commerce Logistics" by Wang et al. 2023
challenges, and future directions, we have gained valuable [2] A Multi-objective Optimization Approach for Carrier Selection in
insights into the opportunities and complexities within this Container Shipping using Random Forest and Deep Neural Network
by Chen et al. 2023
domain.
[3] Ensemble Learning Approach for Carrier Selection in Freight
The methodologies discussed highlight the importance of Transportation using Stacking and Voting by Wu et al. 2022
data preprocessing, feature extraction, model selection, and [4] Rule-based and Machine Learning Hybrid Model for Carrier
evaluation in the development of recommendation systems. Selection in Less-than-Truckload Transportation by He et al. 2022
By employing these methodologies, researchers can build [5] Case-based Reasoning with Reinforcement Learning for Dynamic
Carrier Recommendation in Intermodal Transportation by Li et al.
robust models capable of analyzing historical data and 2021
generating personalized recommendations for carrier-shipper
[6] Genetic Algorithm-based Optimization for Multi-modal Carrier
matching. Selection in Supply Chain Management" by Xu et al. 2020
Algorithms play a crucial role in the effectiveness of [7] Hybrid Explainable Neural Network Approach for Carrier Selection
recommendation systems, offering diverse approaches to in Freight Transportation by Zhang et al. 2020
multilabel classification tasks. From k-nearest neighbors to [8] Hybrid Model with Deep Learning and Rule-based System for Real-
time Carrier Recommendation in E-commerce Logistics by Liu et al.
neural networks, each algorithm brings unique strengths and 2019
capabilities to the table, allowing for the creation of [9] Artificial Intelligence based System on enhancing the Capabilities of
sophisticated recommendation models. Transport System: A Systemic Literature Review, by Muhammad
Zain Malik, Shah Nazir, Habib Ullah Khan 2023.
Datasets serve as the foundation for recommendation
[10] A systematic review and research perspective on recommender
systems, capturing the intricacies of logistics operations and systems by Deepjyoti Roy* and Mala Dutta 2022
providing valuable insights for model training. However, [11] Deep Based Recommender System For Relevant K Pick-up Points, by
challenges such as data quality, availability, and Ayoub Berdeddouch, Ali Yhyaouy, Younes Benanni 2020