Ranks Relevant Files in the Top 10 with 70% Accuracy

On average, CodeSearchFinder-AI successfully ranks one or more relevant code files in the top 10 with 70% accuracy.

Our AI-powered approach analyzes a given service request and corresponding source files by computing two key scores:

  1. Lexical Similarity Score – Measures textual similarity between the service request and code files.
  2. Probabilistic Score – Based on the Vector Space Model, determining relevance through statistical analysis.

Each score is derived from four different search types, each using a distinct set of indexed terms from both the service request and the code file.

To ensure the most accurate ranking, we:

  • Generate eight different ranking combinations by applying these scoring methods.
  • Rank all files in descending order for each combination.
  • Select the best rank for each file across all eight rankings.

Additionally, CodeSearchFinder-AI evaluates each service request and code file individually by analyzing key elements such as:

  • Summary and stack trace
  • Stemming and linguistic variations
  • Code comments and file names

When relevant and available, these factors are leveraged to further optimize ranking accuracy.

Contact us for an online demo