Upload sarimax model with evaluation metrics

README.md

@@ -0,0 +1,40 @@
+# SARIMAX Model for M5 Demand Forecasting
+
+## Overview
+Seasonal ARIMA with eXogenous variables trained on aggregated daily M5 sales data.
+
+## Model Details
+- **Architecture**: SARIMAX(2,1,1)(1,1,1,7)
+- **Training Data**: 1,913 days with 6 exogenous features
+- **Test Period**: 28 days (2016-04-25 to 2016-05-22)
+- **Exogenous Variables**: wday, month, snap_CA, snap_TX, snap_WI, has_event
+
+## Performance
+| Metric | Value |
+|--------|-------|
+| RMSE | 2,759.70 |
+| MAE | 2,260.25 |
+| MAPE | 4.98% |
+| AIC | 35869.68 |
+
+## Key Features
+- Captures autocorrelation and seasonal patterns
+- Exogenous variables provide additional signal
+- Weekly seasonality (s=7) for day-of-week effects
+- Event indicators (holidays, SNAP days) improve accuracy
+
+## Usage
+```python
+import pickle
+import pandas as pd
+
+with open('model.pkl', 'rb') as f:
+    model = pickle.load(f)
+
+forecast = model.forecast(steps=28, exog=exog_future)
+```
+
+## Notes
+- Best performance among the three statistical models
+- Exogenous variables (especially SNAP indicators) significantly improve predictions
+- Larger model size (85MB) due to seasonal components

metrics.json

@@ -0,0 +1,19 @@
+{
+  "rmse": 2759.696905356552,
+  "mae": 2260.247243573586,
+  "mape": 4.980222193545587,
+  "method": "SARIMAX",
+  "order": [
+    2,
+    1,
+    1
+  ],
+  "seasonal_order": [
+    1,
+    1,
+    1,
+    7
+  ],
+  "train_days": 1913,
+  "test_days": 28
+}

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97c55e424c49326ad5989df42aab3a398158b8fbaa730e0a465ebfcc111c8ffe
+size 89436804

model_config.json

@@ -0,0 +1,54 @@
+{
+  "model_name": "SARIMAX",
+  "hyperparameters": {
+    "order": [
+      2,
+      1,
+      1
+    ],
+    "seasonal_order": [
+      1,
+      1,
+      1,
+      7
+    ],
+    "trend": "c",
+    "enforce_stationarity": false,
+    "enforce_invertibility": false
+  },
+  "training_data": {
+    "train_days": 1913,
+    "test_days": 28,
+    "train_start": "2011-01-29 00:00:00",
+    "train_end": "2016-04-24 00:00:00",
+    "exog_features": [
+      "wday",
+      "month",
+      "snap_CA",
+      "snap_TX",
+      "snap_WI",
+      "has_event"
+    ],
+    "aic": 35869.684809082944,
+    "bic": 35941.80233095954
+  },
+  "metrics": {
+    "rmse": 2759.696905356552,
+    "mae": 2260.247243573586,
+    "mape": 4.980222193545587,
+    "method": "SARIMAX",
+    "order": [
+      2,
+      1,
+      1
+    ],
+    "seasonal_order": [
+      1,
+      1,
+      1,
+      7
+    ],
+    "train_days": 1913,
+    "test_days": 28
+  }
+}

predictions.csv

@@ -0,0 +1,29 @@
+ds,yhat,actual
+2016-04-25,38805.11936782724,38793
+2016-04-26,36316.105828214844,35487
+2016-04-27,35752.42080290593,34445
+2016-04-28,36582.001356706554,34732
+2016-04-29,40021.65105203574,42896
+2016-04-30,48196.35281505108,50429
+2016-05-01,51530.0262907313,53032
+2016-05-02,41857.07730659572,43181
+2016-05-03,40467.91078918641,44314
+2016-05-04,37463.81561243717,39601
+2016-05-05,39465.26870813444,40763
+2016-05-06,44250.71209230045,43805
+2016-05-07,53019.85674631836,54239
+2016-05-08,51451.157547362236,45609
+2016-05-09,43474.084010331186,46400
+2016-05-10,37953.66045915283,39379
+2016-05-11,38475.18393370119,42248
+2016-05-12,39468.605711146374,40503
+2016-05-13,41414.537439468375,44073
+2016-05-14,51144.72101008925,54308
+2016-05-15,52881.63756486844,59921
+2016-05-16,39205.3841990734,42362
+2016-05-17,36318.56067550168,38777
+2016-05-18,35983.29108237676,37096
+2016-05-19,36979.27362886479,36963
+2016-05-20,40113.330984365224,42552
+2016-05-21,50100.882300414974,51518
+2016-05-22,50390.02911314174,54338