diff --git a/model_data/optimiser/GainOptimiser.py b/model_data/optimiser/GainOptimiser.py
index 08484774..d5c8a5af 100644
--- a/model_data/optimiser/GainOptimiser.py
+++ b/model_data/optimiser/GainOptimiser.py
@@ -1,18 +1,21 @@
-from mip import Model, xsum, maximize, BINARY
+from mip import Model, xsum, maximize, BINARY, OptimizationStatus
+from utils.logger import setup_logger
+
+logger = setup_logger()
 
 
 class GainOptimiser:
     """
-    This class is used maximise gain, given a constrained cost
+    This class is used to maximise gain, given a constrained cost
     """
 
     def __init__(self, components, max_cost):
         self.components = components
         self.max_cost = max_cost
+        self.cost_constraint = None
         self.m = None
         self.variables = []
         self.solution = []
-
         self.solution_gain = None
         self.solution_cost = None
 
@@ -26,7 +29,6 @@ class GainOptimiser:
             self.components
         ]
 
-        # Set objective
         # This objective is the sum
         # gain_ig * x_ig, where gain_ig represents the gain for ith part in group g
         # and x_ig is the binary decision variable for the ith part in group g
@@ -38,33 +40,58 @@ class GainOptimiser:
             )
         )
 
-        # Add constraints
         # This constrain ensures that sum of cost_ig * x_ig <= C, where cost_ig represents the cost for the ith
         # component
         # in group g, and x_ig is the binary decision variable for the ith component in group g
-        self.m += xsum(
+        cost_expression = xsum(
             item['cost'] * var for group, group_vars in zip(self.components, self.variables) for item, var in
             zip(group, group_vars)
         ) <= self.max_cost
 
-        # At most one item from each group
+        self.cost_constraint = self.m.add_constr(cost_expression)
+
         # This constraint ensures that at most one item from each group is selected
         # This is expressed by summing up the decision variables for each group and ensuring that the sum is <= 1
         for group_vars in self.variables:
             self.m += xsum(var for var in group_vars) <= 1
 
+    def setup_slack(self):
+        # Remove the original cost constraint
+        self.m.remove(self.cost_constraint)
+
+        # Add slack variable
+        s = self.m.add_var(lb=0)
+
+        # Modify the constraint
+        self.m += xsum(
+            item['cost'] * var for group, group_vars in zip(self.components, self.variables) for item, var in
+            zip(group, group_vars)
+        ) + s <= self.max_cost
+
+        # Modify the objective to penalize the use of slack
+        penalty = -10000  # Negative penalty because we are maximizing
+        self.m.objective = maximize(
+            xsum(
+                component['gain'] * var for group, group_vars in zip(self.components, self.variables) for component, var
+                in
+                zip(group, group_vars)
+            ) + penalty * s
+        )
+
     def solve(self):
         # Solve the problem
         self.m.optimize()
 
+        if self.m.status == OptimizationStatus.INFEASIBLE:
+            logger.info("We have an infeasible model, setting up slack model")
+            self.setup_slack()
+            self.m.optimize()
+
         self.solution = [
             item for group, group_vars in zip(self.components, self.variables) for item, var in zip(group, group_vars)
             if
             var.x >= 0.99
         ]
 
-        # Get the selected items
-
         self.solution_gain = self.m.objective.x
         self.solution_cost = sum([component['cost'] for component in self.solution])
-