Strategic and Crowd-Aware Itinerary Recommendation

Abstract

Itinerary recommendation is a complex sequence prediction problem with numerous real-world applications. This task becomes even more challenging when considering the optimization of multiple user queuing times and crowd levels, as well as numerous involved parameters, such as attraction popularity, queuing time, walking time, and operating hours. Existing solutions typically focus on single-person perspectives and fail to address real-world issues resulting from natural crowd behavior, like the Selfish Routing problem. In this paper, we introduce the Strategic and Crowd-Aware Itinerary Recommendation (SCAIR) algorithm, which optimizes group utility in real-world settings. We model the route recommendation strategy as a Markov Decision Process and propose a State Encoding mechanism that enables real-time planning and allocation in linear time. We evaluate our algorithm against various competitive and realistic baselines using a theme park dataset, demonstrating that SCAIR outperforms these baselines in addressing the Selfish Routing problem across four theme parks.

Optimalisasi Rekomendasi Rute Pada Perencanaan Perjalanan Wisata: Studi Pustaka

“…GAP merupakan persentase perbedaan nilai antara nilai BKS (best known solution) yang didapatkan dari penelitian sebelumnya dengan nilai yang didapatkan pada penelitian yang sedang dilakukan (Best). Selain matriks evaluasi di atas, terdapat juga matriks evaluasi yang disesuaikan dengan permasalahan seperti waktu transit (Etransit) [38], distance optimization (DisOp), popularitas lokasi dalam rute (Pop), waktu tunggu pengguna pada lokasi (AvgQt) dan expected utility (Uty) [40].…”

“…Definisi taksonomi didasarkan pada pendekatan penelitian yang dilakukan, jumlah fungsi objektif yang digunakan, faktor konteks yang mempengaruhi dan teknik yang digunakan untuk mendapatkan solusi. Penulis membagi menjadi 2 kelompok pendekatan dalam penelitian rekomendasi rute yaitu (i) penelitian yang berfokus pada proses optimasi rute perjalanan seperti pada penelitian [25], [39], [41] dan (ii) penelitian yang fokus pada optimasi mendapatkan nilai pada tempat wisata yang sesuai dengan personalisasi atau minat pengguna [16], [18], [40]. Selain itu, berdasarkan jumlah fungsi objektif yang digunakan mayoritas penelitian terbagi menjadi 2, yaitu penelitian yang menggunakan satu fungsi objektif dan multi fungsi objektif.…”

Photozilla: A Large-Scale Photography Dataset and Visual Embedding for 20 Photography Styles

“…We intend to collect more information and fuse different types of features, such as captions, locations, and hashtags [6,13], and perform multi-modal analysis and sequence prediction tasks for various applications of the dataset, such as next-POI (Point-Of-Interest) recommendations [14].…”

Urban Crowdsensing using Social Media: An Empirical Study on Transformer and Recurrent Neural Networks

“…Geo-tagged social media has been frequently used for solving various location-based problems, such as predicting the location of a social media posts [6], predicting next visit locations [7] and recommending tour itineraries [8], among others. Similarly, we curate our dataset from mainly geotagged Twitter messages (i.e., tweets) and Flickr photos, which we retrieve using the Twitter and Flickr APIs, respectively.…”