Improving realty management ability based on big data and artificial intelligence decision-making

Area of Science:

• Real Estate Management
• Data Science
• Machine Learning

Background:

• Effective realty management requires analyzing historical purchase and utilization data.
• Identifying valuable data for incremental value and profitable utilization remains a challenge.

Purpose of the Study:

• To propose a knowledge-dependent data processing scheme (KDPS) for precise realty data analysis.
• To enhance the selection and processing of data for improved real estate utilization efficacy.

Main Methods:

• A two-level KDPS was developed for data selection and processing.
• Knowledge from sales, amenities, and market value was integrated.
• Stagnancy and realty values were used for training the data processing system.

Main Results:

• The KDPS improved processing rate by 8.2%, stagnancy detection by 10.25%, success rate by 10.28%, and training ratio by 7%.
• Processing time was reduced by 8.56% compared to existing methods.
• The scheme ensures profitable features and reduced stagnancy time.

Conclusions:

• The KDPS offers a more precise and efficient approach to realty data analysis.
• It effectively mitigates stagnancy and identifies profitable features in real estate.
• This method supports informed decision-making for improved real estate asset management.