Guesty: Property management platform delivers a game changing recommendation system

Qwak was engaged to refine the team's ML model deployment processes, fostering seamless integration and reducing the interdependency between data science and machine learning engineering teams.

In the rapidly evolving landscape of property management technology, optimizing data processes remains paramount. Guesty, a leading player in this domain, faced challenges in streamlining its data science operations and hastening model deployment. This case study delves into Guesty's unique challenges and highlights how a strategic partnership with Qwak provided innovative solutions.

About Guesty

Guesty is an end-to-end platform for property managers and management companies, offering cloud-based tools to simplify operational tasks such as tracking guest check-ins and property revenue, addressing the complex needs of short-term and vacation rentals.


Industry

Property Management, Real Estate, Software / Technology

Use Case

Chatbot based on NLP models
Dynamic pricing based on XGBoost

Model Frameworks

No items found.

Before Qwak we had no standard methodology for productionizing ML models. There was no alignment between the data science and engineering teams and we spent weeks analyzing code and solving errors. Basically, it was a huge mess

Elad Silvas
Data Science Manager
↓1 Week

Time To Production

Zero

Engineering Dependency

100%

Model Uptime

Challenges

  • Establishing synergy between data science teams to hasten model deployment timelines.
  • Each model deployment mandated participation from both data engineering and DevOps teams, significantly protracting the delivery timeframe.
  • The lack of a centralized data science management system led to team misalignment.
  • Guesty's Data Science teams were disproportionately engaged in engineering chores, diverting their focus from core research and model creation.

Solutions

  • Establishing synergy between data science teams to hasten model deployment timelines.
  • Each model deployment mandated participation from both data engineering and DevOps teams, significantly protracting the delivery timeframe.
  • The lack of a centralized data science management system led to team misalignment.
  • Guesty's Data Science teams were disproportionately engaged in engineering chores, diverting their focus from core research and model creation.