← BACK TO PROJECT SHOWCASE
PublicationPublished2025

Profile Matching in Python to Identify Tourist Destinations for the Development of National Tourism

A data-driven tourism prioritization study using Profile Matching and Python across 22 destinations in Indonesia.

RESEARCH OVERVIEW

This paper investigates how Indonesia can prioritize tourism destination development under funding constraints while tourism remains a strategic driver of national economic recovery. The study evaluates 22 destinations across Java, Sumatra, Sulawesi, Bali, Lombok, NTT, and Papua using a Profile Matching approach implemented in Python, based on 7 criteria: accessibility, accommodation, local workforce absorption, information availability, community involvement, technology and innovation, and human resource development. The analysis produces an evidence-based ranking that highlights destinations requiring optimization attention and translates findings into practical improvement priorities for policy and execution.

Journal

AISM Vol. 8(2), 2025

Pages

315-322

DOI

10.15408/aism.v8i2.46683

Destinations Evaluated

22

Criteria

7

Execution Time

0.06s

RESEARCH ARTIFACTS

Paper methodology map
01Research methodology and structured analysis flow
Findings synthesis matrix
02Synthesis matrix from findings to conclusions
Publication insight summary
03Publication summary and recommendation highlights

PROBLEM CONTEXT

Tourism contributes significantly to national revenue, yet not every destination can be optimized at the same time due to budget and infrastructure limitations. Decision-makers need a transparent prioritization model that balances economic impact, destination readiness, and development feasibility across diverse regions.

RESEARCH APPROACH

The research combines literature-grounded criteria design with Profile Matching calculations and Python-based data processing. An ideal profile is defined, gaps are computed against actual destination profiles, weighted scores are aggregated, and destinations are ranked from closest to farthest from the target profile. This approach provides a fast, reproducible, and explainable prioritization workflow without building a full DSS application.

NOVELTY & CONTRIBUTION

  • Identified three high-priority destinations for optimization: Lake Maninjau, Rantepao, and Seminyak
  • Delivered a reproducible national-scale ranking across 22 destinations using 7 weighted criteria
  • Demonstrated efficient processing with Python execution time of approximately 0.06 seconds on standard hardware
  • Provided actionable recommendations covering road access, basic facilities, community participation, HR development, and technology adoption

AUTHOR CONTRIBUTION

  • Problem framing and research scope development
  • Criteria engineering based on tourism development barriers and policy context
  • Profile Matching model implementation and Python-based computation
  • Result interpretation, manuscript development, and publication finalization

STUDY COMPONENTS

COMPONENT 01

Cross-regional tourism dataset covering 22 destinations in Indonesia

COMPONENT 02

Seven-criteria evaluation model with weighted gap computation

COMPONENT 03

Core factor and secondary factor modeling for decision relevance

COMPONENT 04

Transparent ranking output based on total weighted values

COMPONENT 05

Policy-ready recommendation mapping for destination optimization

METHODS & TOOLS

PythonProfile MatchingMCDMPandasData AnalysisAcademic Writing
READ PAPERSUPPLEMENTARY REPOSITORY

RELATED WORKS

Full-Stack

Enterprise Web Platform

A modular business platform engineered for scale and operational speed.

Infrastructure

Infrastructure Readiness Program

Reliability initiative for safer and faster product releases.

Research

Applied Research Initiative

Structured technical research for high-confidence architecture decisions.