diff --git a/churn_model_new/README.md b/churn_model_new/README.md
index 046afc4..fb1a77c 100644
--- a/churn_model_new/README.md
+++ b/churn_model_new/README.md
@@ -25,7 +25,8 @@ The primary functionality is to predict the probability of customer churn. The c
 2. **Install Dependencies**: Make sure you have the required dependencies installed, as specified in the `conda.yml` file.
 
     ```bash
-    conda env create -f main/conda.yaml
+    conda config --set ssl_verify false
+    conda env create -f main/conda.yml
     conda activate churn_model
     ```
 
@@ -34,6 +35,7 @@ The primary functionality is to predict the probability of customer churn. The c
     ```bash
     pip install qwak-sdk
     qwak configure
+    pip install "qwak-inference[batch,feedback]"
     ```
 
 5. **Run the Model Locally**: Execute the following command to test the model locally:
diff --git a/churn_model_new/main/__pycache__/__init__.cpython-39.pyc b/churn_model_new/main/__pycache__/__init__.cpython-39.pyc
new file mode 100644
index 0000000..1f2b6b3
Binary files /dev/null and b/churn_model_new/main/__pycache__/__init__.cpython-39.pyc differ
diff --git a/churn_model_new/main/__pycache__/model.cpython-39.pyc b/churn_model_new/main/__pycache__/model.cpython-39.pyc
new file mode 100644
index 0000000..38ebcce
Binary files /dev/null and b/churn_model_new/main/__pycache__/model.cpython-39.pyc differ
diff --git a/churn_model_new/main/conda.yml b/churn_model_new/main/conda.yml
index 56092b3..4bec6a0 100644
--- a/churn_model_new/main/conda.yml
+++ b/churn_model_new/main/conda.yml
@@ -5,7 +5,9 @@ channels:
 dependencies:
   - python=3.9
   - pip
-  - pandas
+  - pandas=2.2.2
+  - numpy=2.0.0
   - scikit-learn
+  - pybind11>=2.12
   - xgboost
-  - scipy=1.10.1
+  - scipy
diff --git a/churn_model_new/test_model_locally.py b/churn_model_new/test_model_locally.py
index 1c1b2e0..1f99b20 100644
--- a/churn_model_new/test_model_locally.py
+++ b/churn_model_new/test_model_locally.py
@@ -30,6 +30,9 @@
             'Agitation_Level' : 70
         }]
     
+    # Print that it is starting the process
+    print("\n\nPREDICTION STARTING:\n\n")
+
     # Create the DataFrame and convert it to JSON
     df = DataFrame(feature_vector).to_json()