The Power of Renegotiation and Monitoring in Software Outsourcing: Substitutes or Complements?

Monitoring and contract renegotiation are two common solutions for addressing information asymmetry and uncertainty between a client and a vendor of software outsourcing services. Monitoring is mostly applied in time-and-materials contracts, as a basis for inspecting and reimbursing the vendor’s efforts in system development. Renegotiation, by contrast, is deployed in fixed-price and time-and-materials contracts to mitigate the loss of surplus from uncertainty after system development. We investigate the interaction between monitoring and renegotiation and examine the corresponding contract choice problem. We find that the client benefits from renegotiation based on two effects: an uncertainty-resolution effect and a post-development incentive effect , which incentivizes the vendor to exert additional effort in system development. Monitoring does not resolve uncertainty, although it does encourage the vendor to exert additional effort, a pre-development incentive effect . Our analysis shows that the choice of renegotiation or monitoring depends on the interactions of the above effects, which are moderated by the renegotiation cost, monitoring cost, and bargaining power in renegotiation. When renegotiation cost is low: if the client has high bargaining power and low monitoring cost, monitoring and renegotiation are complements and both are selected; otherwise, the two instruments are substitutes and contract renegotiation is preferred. When renegotiation cost is high: monitoring substitutes for renegotiation and the client only chooses monitoring if the cost to do it is low; or else neither is used. Overall, this research shows that four appropriate contract strategies should be used under somewhat different circumstances. We further analyze the impacts of some other key aspects of software outsourcing and extend the base model to address two alternative situations to show the robustness of our findings. The results apply to a range of software reliability growth models , including when machine learning or cloud computing are used.