Data-Driven Destination Recommender Systems Linus W. Dietz - - PowerPoint PPT Presentation

Data-Driven Destination Recommender Systems

Linus W. Dietz Technical University of Munich Department of Informatics Chair of Connected Mobility (I11) UMAP’18, Singapore July 10, 2018

Introduction

Problem Recommend composite trips of global travel destinations “I want to travel to South-East Asia for six weeks in summer to experience culture, good food and go hiking in the mountains. I have a budget of $1500.” Motivation Independent travel planning is complex, information is scattered, outdated, and

• f uncertain quality

Challenges

Find distinct touristic regions Classification of tourist destinations User modeling with little user effort Recommendation algorithm

c

• Created by Freepik

Linus W. Dietz (TUM) 2

Overview

Items User Algorithms

Item discovery Item classification Effective and effortless

preference elicitation

Traveler clustering Content-based filtering Constraint satisfaction Diversity of activities Durations of item

consumption

Linus W. Dietz (TUM) 3

Data Mining & Domain Modeling

Recommendation items: set of travel regions Combination of heterogeneous data sources Item discovery

Mismatch between political regions and tourist destinations! Employ hierarchical region tree Make the granularity of destinations dependent on the query area

Item characterization

What are the characteristics, attractions, and activities of a destination? Aggregation based on single points of interests What is the typical duration of stay at a destination? Analyze tourist mobility patterns for domain understanding

Evaluation: Offline comparison with crowdsourcing and expert knowledge

Contribution: framework for data-driven recommender systems

Linus W. Dietz (TUM) 4

User Modeling

Preference elicitation

Which activities are best suited for a traveler? How can traveling preferences be elicited effectively with little effort?

Traveler clustering

What are the relevant features to characterize travelers? What distinct types of travelers are there? How can the pace of the travel itinerary be personalized based on past trips?

Evaluation: Controlled lab experiments

Contribution: Novel approaches for domain-specific user modeling

Linus W. Dietz (TUM) 5

Recommendation Algorithms

Content-based recommendation under constraints. Knapsack problem! Personalize item consumption durations Ensure sufficient diversity within a trip Measure the benefits of explaining recommendations and critiquing Evaluation: Measure user satisfaction in an online field study

Contribution: Constraint-based algorithms for composite trips

Linus W. Dietz (TUM) 6

Current Progress

Investigated traveler mobility patterns

Linus W. Dietz (TUM) 7

Current Progress

Preliminary investigation of durations of stay

Days Kuwait Dominican Rep. Cyprus Azerbaijan Costa Rica Ghana Kazakhstan Paraguay Australia Belarus Saudi Arabia Turkey Martinique Brazil United States Russia Colombia Mexico Philippines Canada New Zealand Indonesia Japan Argentina China United Kingdom Malaysia Venezuela Thailand Spain Singapore

• Un. Arab Emirates

Italy Ireland Germany Sweden France Czech Rep. Finland Netherlands Switzerland Belgium Denmark Hungary Estonia 3 6 9 12 15 18 21 500 1500 2500 3500 Observations mean days

• bservations

Linus W. Dietz (TUM) 8