Rental Credit Score via CNN Analysis of Tenant History
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional tenant screening methods are limited by incomplete information, often failing to detect instances of nonpayment and other relevant behavioral data, which can lead to inadequate assessment of potential tenants.
Innovation Solution
A computer-implemented method using a convolutional neural network (CNN) to analyze rental history data, generating a rental credit score by averaging category scores, and incorporating time factors and behavior scores, with the option to create a non-fungible token (NFT) authenticated by a blockchain for secure transmission to lenders or insurance providers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional background checks are used for tenant screening, then the screening process is simple and quick, but the information available is limited and incomplete, failing to detect instances of nonpayment and other relevant behavioral data
Solution Approach 1:
The patent combines multiple data sources including rental history, payment records, behavioral data, and traditional background check information into a unified tenant screening system. This merging of diverse information sources resolves the contradiction by providing comprehensive information without requiring separate complex systems for each data type.
Solution Approach 2:
The screening system is designed to perform multiple functions: analyzing payment history, evaluating behavioral data, assessing rental history, and generating comprehensive risk assessments. This multi-functional approach provides complete information while consolidating what would otherwise require multiple separate screening tools.
2Measurement precision
If comprehensive rental history data is collected and analyzed using CNN, then the accuracy of tenant screening is improved, but the computational complexity and data processing requirements increase
Solution Approach 1:
The patent replaces traditional mechanical screening methods with machine learning algorithms, specifically convolutional neural networks (CNN), to automatically analyze rental history data. This substitution improves assessment accuracy by detecting patterns in comprehensive data that would be difficult for manual review to identify, while the automated nature of the system manages computational complexity through algorithmic efficiency.
Solution Approach 2:
The system transforms raw rental history data into standardized numerical parameters and features that can be processed by the CNN. By changing the parameter representation of rental data (converting unstructured data into structured numerical formats), the system enables accurate analysis while optimizing computational efficiency for the neural network processing.
Data Source
AI summary
A computer-implemented method of recording voter selections includes receiving data of a rental history for a tenant. The data of the rental history for the tenant includes at least two data sets selected from past rent owed, payment history, length of time at a previous residence, history of the tenant being a primary renter, history of the tenant being a co-tenant, history of the tenant being a co-signer, occurrences of judgments against the tenant, or behavior of the tenant at the previous residence. The method includes assigning a category score to each data set of the at least two data sets using a convolutional neural network (CNN). The CNN determines an average category score for the data sets by averaging the assigned category scores for the data sets. A rental credit score is generated based on the determined average category score for the data sets.