Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Multi-tiered Solution for Personalized Baggage Item Recommendations using FastText and Association Rule Mining

Mudavath Ravi, Atul Negi

TL;DR

This work presents a multi-phase Air Travel Baggage Recommender System (ATRS) that integrates FastText embeddings with Association Rule Mining to deliver personalized packing suggestions. By building a baggage vocabulary from web-scraped airline data (712 items across 43 categories) and progressively combining content-based filtering with ARM across four phases, the framework supports context-aware, real-time, and user-feedback-driven recommendations. The methodology emphasizes data gathering, text-based similarity, transaction mining, and rule-driven personalization, evaluated through metrics such as coverage, support, confidence, lift, and leverage. The proposed ATRS demonstrates improved relevance and user satisfaction in baggage recommendations, supporting efficient packing, compliance with airline constraints, and potential for targeted marketing and product optimization in air travel.

Abstract

This paper introduces an intelligent baggage item recommendation system to optimize packing for air travelers by providing tailored suggestions based on specific travel needs and destinations. Using FastText word embeddings and Association Rule Mining (ARM), the system ensures efficient luggage space utilization, compliance with weight limits, and an enhanced travel experience. The methodology comprises four phases: (1) data collection and preprocessing with pre-trained FastText embeddings for text representation and similarity scoring (2) a content-based recommendation system enriched by user search history (3) application of ARM to user interactions to uncover meaningful item associations and (4) integration of FastText and ARM for accurate, personalized recommendations. Performance is evaluated using metrics such as coverage, support, confidence, lift, leverage, and conviction. Results demonstrate the system's effectiveness in providing relevant suggestions, improving customer satisfaction, and simplifying the packing process. These insights advance personalized recommendations, targeted marketing, and product optimization in air travel and beyond.

A Multi-tiered Solution for Personalized Baggage Item Recommendations using FastText and Association Rule Mining

TL;DR

This work presents a multi-phase Air Travel Baggage Recommender System (ATRS) that integrates FastText embeddings with Association Rule Mining to deliver personalized packing suggestions. By building a baggage vocabulary from web-scraped airline data (712 items across 43 categories) and progressively combining content-based filtering with ARM across four phases, the framework supports context-aware, real-time, and user-feedback-driven recommendations. The methodology emphasizes data gathering, text-based similarity, transaction mining, and rule-driven personalization, evaluated through metrics such as coverage, support, confidence, lift, and leverage. The proposed ATRS demonstrates improved relevance and user satisfaction in baggage recommendations, supporting efficient packing, compliance with airline constraints, and potential for targeted marketing and product optimization in air travel.

Abstract

This paper introduces an intelligent baggage item recommendation system to optimize packing for air travelers by providing tailored suggestions based on specific travel needs and destinations. Using FastText word embeddings and Association Rule Mining (ARM), the system ensures efficient luggage space utilization, compliance with weight limits, and an enhanced travel experience. The methodology comprises four phases: (1) data collection and preprocessing with pre-trained FastText embeddings for text representation and similarity scoring (2) a content-based recommendation system enriched by user search history (3) application of ARM to user interactions to uncover meaningful item associations and (4) integration of FastText and ARM for accurate, personalized recommendations. Performance is evaluated using metrics such as coverage, support, confidence, lift, leverage, and conviction. Results demonstrate the system's effectiveness in providing relevant suggestions, improving customer satisfaction, and simplifying the packing process. These insights advance personalized recommendations, targeted marketing, and product optimization in air travel and beyond.
Paper Structure (65 sections, 31 equations, 11 figures, 11 tables, 4 algorithms)

This paper contains 65 sections, 31 equations, 11 figures, 11 tables, 4 algorithms.

Table of Contents

  1. Introduction
  2. About ATRS
  3. Motivation of Baggage Module in ATRS
  4. Contributions
  5. Related work of the Air Travel Baggage Recommender Systems
  6. ATRS Terminology and Taxonomy of Terms
  7. How ATRS is useful
  8. Problem statement
  9. Objectives and Constraints of ATRS
  10. Research Gaps in Air Travel Baggage Recommendation Systems
  11. Contextual Understanding
  12. Integration of Real-Time Data
  13. Personalization and User Profiling
  14. Multi-Modal Recommendations
  15. User Interaction and Feedback
  16. ...and 50 more sections

Figures (11)

  • Figure 1: ATRS Concept
  • Figure 2: ATRS Workflow
  • Figure 3: Distribution of Carry on items
  • Figure 4: Distribution of Check in items
  • Figure 5: Distribution of Prohibited items
  • ...and 6 more figures