Energy Based Logic Mining Analysis with Hopfield Neural Network for Recruitment Evaluation

Area of Science:

• Artificial Intelligence
• Data Mining
• Computational Logic

Background:

• Effective recruitment evaluation is crucial for organizational success.
• Understanding factors driving systematic recruitment requires advanced data analysis.
• Electronic (E) recruitment data offers a rich source for identifying recruitment drivers.

Purpose of the Study:

• To propose an energy-based k-satisfiability reverse analysis model using a Hopfield neural network.
• To extract relationships between factors within an E-recruitment dataset.
• To identify dominant attributes contributing to positive recruitment outcomes.

Main Methods:

• Representing E-recruitment data attributes using k-satisfiability logical representations (2-SAT and 3-SAT).
• Employing an energy-based k-satisfiability reverse analysis incorporating a Hopfield neural network.
• Evaluating the model's correctness, robustness, and accuracy on an insurance agency's E-recruitment data from Malaysia.

Main Results:

• The proposed model successfully extracted relationships between recruitment factors.
• Experimental simulations demonstrated the effectiveness of the approach.
• The energy-based k-satisfiability reverse analysis with Hopfield neural network proved robust in identifying dominant recruitment attributes.

Conclusions:

• The developed approach is effective for extracting dominant attributes related to positive recruitment.
• The Hopfield neural network-based method provides a robust framework for analyzing E-recruitment data.
• This technique offers valuable insights for improving recruitment strategies in the insurance sector.