diff --git a/azure-pipelines.yml b/azure-pipelines.yml
index 5c4218dec..98f2b4e11 100644
--- a/azure-pipelines.yml
+++ b/azure-pipelines.yml
@@ -255,7 +255,7 @@ jobs:
 - template: build_tools/azure/posix.yml
   parameters:
     name: macOS
-    vmImage: macOS-11
+    vmImage: macOS-12
     dependsOn: [linting, git_commit]
     condition: |
       and(
diff --git a/conftest.py b/conftest.py
index 45a5ce679..0dc6e5a23 100644
--- a/conftest.py
+++ b/conftest.py
@@ -7,7 +7,14 @@
 
 import os
 
+import numpy as np
 import pytest
+from sklearn.utils.fixes import parse_version
+
+# use legacy numpy print options to avoid failures due to NumPy 2.+ scalar
+# representation
+if parse_version(np.__version__) > parse_version("2.0.0"):
+    np.set_printoptions(legacy="1.25")
 
 
 def pytest_runtest_setup(item):
diff --git a/doc/whats_new/v0.12.rst b/doc/whats_new/v0.12.rst
index fd95a4fb8..fb79497d8 100644
--- a/doc/whats_new/v0.12.rst
+++ b/doc/whats_new/v0.12.rst
@@ -1,5 +1,19 @@
 .. _changes_0_12:
 
+Version 0.12.4
+==============
+
+**October 4, 2024**
+
+Changelog
+---------
+
+Compatibility
+.............
+
+- Compatibility with NumPy 2.0+
+  :pr:`1097` by :user:`Guillaume Lemaitre <glemaitre>`.
+
 Version 0.12.3
 ==============
 
diff --git a/imblearn/_version.py b/imblearn/_version.py
index 19c405e4b..ff7e11ace 100644
--- a/imblearn/_version.py
+++ b/imblearn/_version.py
@@ -22,4 +22,4 @@
 # 'X.Y.dev0' is the canonical version of 'X.Y.dev'
 #
 
-__version__ = "0.12.3"
+__version__ = "0.12.4"
diff --git a/imblearn/metrics/pairwise.py b/imblearn/metrics/pairwise.py
index 11f654f02..40f099258 100644
--- a/imblearn/metrics/pairwise.py
+++ b/imblearn/metrics/pairwise.py
@@ -161,7 +161,7 @@ def fit(self, X, y):
                     f"elements in n_categories and {self.n_features_in_} in "
                     f"X."
                 )
-            self.n_categories_ = np.array(self.n_categories, copy=False)
+            self.n_categories_ = np.asarray(self.n_categories)
         classes = unique_labels(y)
 
         # list of length n_features of ndarray (n_categories, n_classes)
diff --git a/imblearn/utils/estimator_checks.py b/imblearn/utils/estimator_checks.py
index 570427759..2fc893391 100644
--- a/imblearn/utils/estimator_checks.py
+++ b/imblearn/utils/estimator_checks.py
@@ -309,7 +309,7 @@ def check_samplers_sparse(name, sampler_orig):
     sampler = clone(sampler)
     X_res, y_res = sampler.fit_resample(X, y)
     assert sparse.issparse(X_res_sparse)
-    assert_allclose(X_res_sparse.A, X_res, rtol=1e-5)
+    assert_allclose(X_res_sparse.toarray(), X_res, rtol=1e-5)
     assert_allclose(y_res_sparse, y_res)
 
 
diff --git a/setup.cfg b/setup.cfg
index 671e45e70..5cd5d6139 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.12.3
+current_version = 0.12.4
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<dev>\d+))?
 serialize =