An Eco-Friendly Tourism Trip Planner Driven by Z-Number Uncertainty: Evidence from Baku, Dubai, Abu Dhabi, Tashkent, and Istanbul

Aziz Nuriyev; Sherzod Turaev; Saja Al-Dabet; Mary John; Kanan Qasimzade; Alihuseyn Orujzada; Fatima Alblooshi; Aisha Al Ali

physics.soc-phOct 21, 2026

An Eco-Friendly Tourism Trip Planner Driven by Z-Number Uncertainty: Evidence from Baku, Dubai, Abu Dhabi, Tashkent, and Istanbul

Authors: Aziz Nuriyev, Sherzod Turaev, Saja Al-Dabet, Mary John, Kanan Qasimzade, Alihuseyn Orujzada, Fatima Alblooshi, Aisha Al Ali

Organizations: BA Programs, Azerbaijan State Oil and Industry University, Baku, Azerbaijan · College of Computing and Artificial Intelligence, United Arab Emirates University, Al Ain, United Arab Emirates · Department of Artificial Intelligence, Aqaba University of Technology, Aqaba, Jordan · Academic Support Department, Abu Dhabi Polytechnic, Abu Dhabi, United Arab Emirates

Abstract

Deployed tourism trip planners ingest travel times and ratings as exact numbers, although routing services return travel times that vary with the hour of departure and a platform rating may rest on a handful of reviews or on hundreds of thousands. We present an eco-friendly trip planner that represents both quantities as Z-numbers, which pair a fuzzy restriction on a value with a fuzzy reliability on the evidence behind it, and that constructs them directly from routing-service observations at six departure hours and from platform review counts rather than from linguistic elicitation. A hybrid loss combines score, carbon, travel-time, and reliability terms, and an adaptive large neighborhood search returns single-day itineraries through a conversational front end. We compare the planner with a crisp-mean baseline under an identical optimizer in Baku, Dubai, Abu Dhabi, Tashkent, and Istanbul, with fifteen points of interest and thirty seeds per city, and we evaluate the selected itineraries on their trip carbon and their total travel time. Pooled over 150 seed-paired runs, the planner lowers trip carbon from 3.24 to 2.61 kg (19.3%, Wilcoxon p = 0.017; city-clustered bootstrap interval 6.4% to 26.7%) and travel time from 123 to 109 minutes per trip (11.5%, p = 2.8e-10; interval 5.0% to 18.2%). The travel-time reductions survive a Holm correction in Baku, Istanbul, and Abu Dhabi; the carbon reduction is significant in Baku and large but uncertain in the dispersed catalogs of Dubai and Abu Dhabi; and neither metric changes in Tashkent. Review counts are estimates of at least 3,000 for every point of interest, so rating reliability does not vary, and with a single baseline, the results establish feasibility and direction rather than a general advantage. Code, routing caches, frozen routing tables, and per-seed results are openly released.

Figures & tables

City	Hotel base	Currency	Budget	UTC	Taxi base	Per km	Per min
Baku	Badamdar Hotel	AZN	150	$+4$	1.0	2.0	0.1
Dubai	Address Downtown	AED	500	$+4$	12.0	1.96	0.5
Abu Dhabi	Emirates Palace	AED	500	$+4$	12.0	1.82	0.5
Tashkent	Hotel Uzbekistan	UZS	750,000	$+5$	5,000	3,500	500
Istanbul	Four Seasons Sultanahmet	TRY	5,000	$+3$	27.5	15.0	5.0

Table 1: Per-city configuration. The hotel base is the origin and destination of every itinerary; the budget is the monetary soft constraint in local currency; the three taxi parameters define the linear taxi-cost model.

City	Observations	Cache size
Baku	7,145	17 MB
Dubai	6,206	24 MB
Abu Dhabi	5,708	22 MB
Tashkent	2,325	4 MB
Istanbul	5,026	12 MB
Total	26,410	79 MB

Table 2: Released routing caches: number of cached Routes API observations and file size per city.

City	ZN-Full	B1	Change	$p$	$p_{\mathrm{Holm}}$	$d$
Baku	$2.45\pm 0.51$	$2.99\pm 0.80$	$-18.1\%^{**}$	0.007	0.0498	$-0.51$
Tashkent	$2.62\pm 0.53$	$2.66\pm 0.69$	$-1.4\%$	0.935	1.000	$-0.04$
Istanbul	$0.80\pm 0.60$	$0.81\pm 0.67$	$-1.1\%$	0.854	1.000	$-0.01$
Dubai	$3.93\pm 1.67$	$5.06\pm 2.68$	$-22.4\%$	0.241	0.964	$-0.31$
Abu Dhabi	$3.27\pm 2.21$	$4.67\pm 2.66$	$-30.0\%$	0.129	0.647	$-0.37$

Table 3: Trip carbon footprint (kg of CO 2 ), mean

\pm

standard deviation over thirty seeds. Change is the relative change of the ZN-Full mean against the B1 mean;

p

is the two-sided seed-paired Wilcoxon test;

p_{\mathrm{Holm}}

is adjusted over the ten per-city tests of Tables 3 and 4 ;

d

is Cohen’s

d

for the paired differences. ∗∗ significant after the Holm correction.

City	ZN-Full	B1	Change	$p$	$p_{\mathrm{Holm}}$	$d$
Baku	$125.5\pm 10.6$	$140.6\pm 10.7$	$-10.7\%^{**}$	$1.8\times 10^{-5}$	$1.8\times 10^{-4}$	$-1.16$
Tashkent	$84.5\pm 5.8$	$84.0\pm 7.5$	$+0.6\%$	0.773	1.000	$+0.05$
Istanbul	$98.3\pm 16.9$	$115.9\pm 25.1$	$-15.2\%^{**}$	0.001	0.010	$-0.69$
Dubai	$143.6\pm 28.8$	$153.7\pm 25.2$	$-6.6\%$	0.080	0.482	$-0.28$
Abu Dhabi	$92.4\pm 28.8$	$120.9\pm 20.5$	$-23.5\%^{**}$	$2.4\times 10^{-5}$	$2.1\times 10^{-4}$	$-0.89$

Table 4: Total travel time per trip (minutes), mean

\pm

standard deviation over thirty seeds; columns as in Table 3 .

Figure 1: Trip carbon footprint per city for the crisp-mean baseline (B1) and the Z-number planner (ZN-Full): mean and one standard deviation over thirty seeds, with the relative change and the two-sided seed-paired Wilcoxon

p

-value.

Metric	ZN-Full	B1	Change	$p$	Cluster 95%
Trip carbon (kg CO 2 )	$2.61\pm 1.66$	$3.24\pm 2.33$	$-19.3\%$	0.017	$[-26.7\%,-6.4\%]$
Travel time (min per trip)	$108.9\pm 30.0$	$123.0\pm 30.5$	$-11.5\%$	$2.8\times 10^{-10}$	$[-18.2\%,-5.0\%]$
POIs per plan	6.06	6.24
Carbon per visited POI (kg)	0.43	0.52
Travel minutes by car	47.0%	45.0%
Travel minutes on foot	26.6%	20.6%

Table 5: Pooled analysis over five cities and thirty seeds (

n=150

pairs).

p

is the two-sided Wilcoxon test over the pooled pairs; the cluster interval resamples the five cities (10,000 draws) and is given for the relative change of the mean. Mode shares are shares of total travel minutes.

Figure 2: Paired differences, ZN-Full minus B1, for (a) trip carbon and (b) travel time per trip. Circles are per-city mean differences over thirty seeds with 95%

t

-intervals; squares are the pooled mean difference with a 95% city-clustered bootstrap interval. Intervals that exclude zero on the favorable side are drawn in blue.

Travel Planning

See all 22 papers

TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning
Jul 29, 2026Jinhu Qi, Wentao Zhang, Siu Man Ng +4Tool-Use Evaluation LLM Agent Evaluation
The Chinese University of Hong Kong Hong Kong, China · Macao Polytechnic University Macau, China
Replan, Repair, or Edit? A Unified Empirical Evaluation of Travel Agents for Itinerary Revision under Resource Disruptions
Sep 17, 2026Xiaofei Yuan, Yan Zhang, Shaobo Qiao +7LLM Planning Travel Planning
Euler AI · University of New South Wales · University of Sydney +1
From Feasibility to Desirability: Plan, Learn, Adapt (PLA) Framework for Personalized On-Device Itinerary Generation
Jul 17, 2026Himel Dev, Tanmoy Sen, Madhusudan Basak +1Travel Planning User Preference Modeling
Tech LLC · University of Virginia · University of Massachusetts Amherst

Jul 29, 2026J/K move · Enter open · S save

TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning

Jinhu Qi, Wentao Zhang, Siu Man Ng, Feiyang Xu+3

The Chinese University of Hong Kong Hong Kong, China · Macao Polytechnic University Macau, China

Tool-Use Evaluation LLM Agent Evaluation Travel Planning LLM Agent Planning

Open paper AskPDF arXiv

Travel planning is a demanding stress test for tool-using LLM agents: a usable itinerary is a single artifact that must be right along many axes at once - every flight, hotel, and attraction must exist and be bookable, the days must be physically traversable, the total must clear a budget, and the plan must serve a traveler whose needs are only partly stated. Existing agent benchmarks reward these properties one at a time and grade the final output with soft or LLM-judged rubrics, which cannot certify that a returned plan is executable and are neither reproducible nor auditable. We introduce TREK (Travel Reasoning and Evaluation Kit), a benchmark for feasible itinerary synthesis: producing a single plan that is jointly constraint-correct, hallucination-free, spatio-temporally executable, budget-valid, and responsive to the traveler's unstated persona needs. TREK comprises 800 multi-constraint tasks - 533 feasible and 267 provably infeasible with typed route/entity/budget causes - over a synthetic, internally consistent knowledge base of 212,530 records across 375 cities and 13 personas, served through a production-style tool sandbox of validated RESTful APIs. Every task is scored by a fully deterministic, rule-based evaluator with no LLM judge and ships a human-verified gold reference that scores a perfect 1.0 under that same evaluator, so the ceiling is demonstrably achievable and every remaining gap is an agent limitation rather than scorer strictness. Evaluating 15 LLM agents across nine constraint dimensions, we find that even the strongest (GPT-5.6) produces a fully-feasible plan on only 46.2% of solvable tasks, with a median of 6.6% and a floor of 0.0%; satisfying travelers' unstated needs emerges as the universal bottleneck, unsolved even at the frontier. We release the dataset, tool sandbox, deterministic evaluator, and agent code as a fully reproducible benchmark.

Abstract

Travel Planning

Explore similar work

TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning

Replan, Repair, or Edit? A Unified Empirical Evaluation of Travel Agents for Itinerary Revision under Resource Disruptions

From Feasibility to Desirability: Plan, Learn, Adapt (PLA) Framework for Personalized On-Device Itinerary Generation