Search Results Page Hotel Recommendations:

utilizing AI to improve recommendation systems and alleviate decision fatigue in users.

Reimagined with ML & AI

UI Design

6 weeks

@ tiket.com

ℹ️ Context

tiket.com is one of the largest and most comprehensive online travel companies in Indonesia providing flight, train, accommodation booking, event ticketing, car rental, and other travel essentials

This redesign was done as a capstone project completed over the course of 10 weeks by a group of three interns. We were assigned to come up with an explorative solution to the main question:

How can the mobile interface be improved to maximize the capabilities of the already existing Machine Learning / Artificial Intelligence systems at tiket.com?

In providing a solution to this, we aim to in turn (1) improve user experience and (2) retain user engagement.

💡Background

1. Understanding Machine Learning (ML) / Artificial Intelligence (AI), and its capabilities in the OTA industry.

After doing our desk research, we discovered that a majority of online travel agencies utilize AI for a better user experience, particularly for curating recommendations for users.

Users are constantly looking for personalized content. (Bozhuk et al., 2020)

(This research studied the current conditions of the tourism industry from consumers’ behaviors.)

2. Understanding the existing ML/AI systems @ tiket.com

The tiket.com Data Science team has numerous ML/AI engines with functions ranging from recommendation to segmentation, detection, natural language processing, pricing, and prediction.

Because a majority of our earlier research pointed towards the direction of user-centered recommendations, we wanted to pick an ML/AI system that could help us better provide recommendations.

Simultaneously, we wanted to pick a system that hadn’t been translated in a design perspective for users to visually see and appreciate.

⚠️ Problem

1. Understanding current problems @ tiket.com

Hotel Funnel Analysis:

An analysis on User Retention and Drop-off Rates from the Search Results Page (SRP) to Purchase Form for Hotels

(Due to a Non-Discoluser Agreement, I’m unable to specify the exact numbers and percentage of users from this data.)

The biggest drop-off rate of users occured in the Room Listing Page.

Our team consulted the lead UX Researcher from this project to ask about any secondary conclusions or findings from the data and key points that we had originally overlooked were heavily correlated with what users did AFTER they had dropped off from that point:

  1. Relevance Issue

    • Some users input the words “child” or “family” on the search form before they dropped-off.

  2. Uncertainty Issue

    • Some users are uncertain about what they’re looking for and leave the Room Listing Page to change destinations on the Search Results Page.

  3. Benefit Issue

    • Some users second-guess the benefits they’re receiving from the hotels they think about choosing and have the mindset that they might possibly find a better deal.

2. Empathetic Data Analysis: Breaking Down Information into User Insights

3. The ML/AI system we chose: Cygnus

Cygnus - Hotel User Segmentation

  • Categorizes users from multiple factors such as (1) click behavior, (2) transactions, (3) geolocation, and (4) their hotel booking process

  • To ensure accuracy and relevancy, the user segmentation models are run monthly, updating user clusters accordingly.

Although not directly related to user-centered recommendations, we decided that this aspect of understanding our users’ behavior and personality was an area of untapped potential for developing an impressive recommendation system.

🔍 A Look into Cygnus

Cygnus’ User Segments

  1. Limited transaction frequency

  2. Budget-conscious

  3. Indifferent to Promotions

  4. Indifferent to Credit Cards

  5. Preference for Standard Hotels

  6. Use of Budget Hotel Filter

  1. Frequent transactions

  2. Budget-conscious

  3. Promotion-Aware

  4. Indifferent to Credit Cards

  5. Preference for Standard Hotels

  6. Use of Luxury Hotel Filter

  1. High-Spending

  2. Promo Hunter

  3. Moderate Credit Card usage

  4. Preference for Luxury Hotels

💭 Our Proposal

Each user segment will have a different Search Results Page UI, with different recommendations specifically catered towards their interests and concerns.

Tailoring

Next

Packpoint