| description abstract | In the construction industry, the advent of teleoperation and robotic technologies is revolutionizing traditional recruitment practices, introducing new criteria for identifying qualified workers. This evolution presents significant challenges for employers aiming to recruit workers who can maximize organizational utility. Although contract theory offers a promising solution to these challenges, its inherent self-disclosure property could inadvertently lead to privacy breaches, such as revealing gender-related information. Such disclosure risk might intensify existing biases, notably gender bias, within the sector. To this end, we proposed deep reinforcement learning (DRL)-based contract theory. Firstly, the trained DRL model will produce unpredictable contract bundles, restricting employers’ access to workers’ privacy. Subsequently, to ensure employers adopt DRL-based contract theory, we utilized blockchain to supervise contract bundle generation. Finally, given that the DRL models are homogenous among employers, we integrated transfer learning to reduce unnecessary overhead. Simulation experiments conducted using US labor force statistical data demonstrated that our work can effectively mitigate potential gender bias by augmenting the contract selection rights for female workers from 72.73% and 60% to 96.97% and 95% in comparison with traditional contract theory while maximizing employers’ utility. In addition, with the integration of transfer learning, the training overhead of DRL-based contract theory can decrease by 50%. The meaning and significance of the results lie in the innovative integration of contract theory, deep reinforcement learning, and transfer learning into the recruitment framework, significantly advancing the body of knowledge in unbiased workforce development. | |
