diff --git a/README.md b/README.md
index 0c4a4d6..d2bf194 100644
--- a/README.md
+++ b/README.md
@@ -52,6 +52,13 @@ The model expects a CSV training set with the following columns and data:
 # Installation 
 `pip install git+https://github.com/USDepartmentofLabor/soii_neural_autocoder.git`
 
+## Alternatively, with conda
+- clone the repository wherever you'd like to use it  
+- navigate to the repository
+- `conda create env -f env`  
+- `conda-develop . -n bls_ml`  
+- `conda activate bls_ml`
+
 # Example Usage
 Modify the `data_file` variable in `examples/big_single_seq_180_lr4e-4.py` to point
 to an appropriately formatted training dataset, or leave as is to use the dummy
diff --git a/env.yml b/env.yml
new file mode 100644
index 0000000..ee96312
--- /dev/null
+++ b/env.yml
@@ -0,0 +1,21 @@
+name: bls_ml
+channels:
+  - conda-forge
+  - defaults
+
+dependencies:
+  - python=3.6
+  - nltk
+  - nltk_data
+  - pyyaml
+  - pandas
+  - keras
+  - tensorflow-gpu
+  - pip
+  - jupyterlab
+  - pytest
+  - pytest-cov
+  - black
+  - pylint
+  - scikit-learn
+  - sphinx