Picture of mobile phone running fintech app

Fintech: Open Access research exploring new frontiers in financial technology

Strathprints makes available Open Access scholarly outputs by the Department of Accounting & Finance at Strathclyde. Particular research specialisms include financial risk management and investment strategies.

The Department also hosts the Centre for Financial Regulation and Innovation (CeFRI), demonstrating research expertise in fintech and capital markets. It also aims to provide a strategic link between academia, policy-makers, regulators and other financial industry participants.

Explore all Strathclyde Open Access research...

A hybrid integer and constraint programming approach to solve nurse rostering problems

Rahimian, Erfan and Akartunali, Kerem and Levine, John (2017) A hybrid integer and constraint programming approach to solve nurse rostering problems. Computers & Operations Research, 82. pp. 83-94. ISSN 0305-0548

[img] Text (Rahimian-etal-COR-2017-A-hybrid-integer-and-constraint-programming-approach)
Accepted Author Manuscript
Restricted to Repository staff only until 27 July 2018.
License: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 logo

Download (609kB) | Request a copy from the Strathclyde author


The Nurse Rostering Problem can be defined as assigning a series of shift sequences (schedules) to several nurses over a planning horizon according to some limitations and preferences. The inherent benefits of generating higher-quality schedules are a reduction in outsourcing costs and an increase in job satisfaction of employees. In this paper, we present a hybrid algorithm, which combines Integer Programming and Constraint Programming to efficiently solve the highly-constrained Nurse Rostering Problem. We exploit the strength of IP in obtaining lower-bounds and finding an optimal solution with the capability of CP in finding feasible solutions in a co-operative manner. To improve the performance of the algorithm, and therefore, to obtain high-quality solutions as well as strong lower-bounds for a relatively short time, we apply some innovative ways to extract useful information such as the computational difficulty of in- stances and constraints to adaptively set the search parameters. We test our algorithm using two different datasets consisting of various problem instances, and report competitive results benchmarked with the state-of-the-art algorithms from the recent literature as well as standard IP and CP solvers, showing that the proposed algorithm is able to solve a wide variety of instances effectively.