Eymdeyy commited on
Commit
d896a52
·
verified ·
1 Parent(s): 1f0d00c

Update model card with benchmarks and use case images

Browse files
Files changed (1) hide show
  1. README.md +23 -5
README.md CHANGED
@@ -44,6 +44,18 @@ print(resp.json()["forecast"]["mean"])
44
  # [171.2, 174.5, 177.8, 181.0, 184.3, 187.6, 190.8]
45
  ```
46
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  ## Models
48
 
49
  | Model | Credits | Best For |
@@ -60,8 +72,14 @@ Evaluated via sliding-window backtesting (5 windows) on public datasets.
60
  | Dataset | Model | Horizon | MAE | RMSE | MAPE | sMAPE |
61
  |---------|-------|---------|-----|------|------|-------|
62
  | ett_h1 | arima | 24 | 2.4524 | 2.9405 | 10.12% | 10.74% |
 
 
63
  | exchange_rate | arima | 30 | 0.0085 | 0.0100 | 1.13% | 1.13% |
 
 
64
  | m5_sample | arima | 14 | 9.0427 | 10.5617 | 7.63% | 7.43% |
 
 
65
 
66
  Datasets: ETT-h1 (electricity transformer temperature), Exchange Rate (8 currencies),
67
  M5 (retail sales). All results are out-of-sample.
@@ -81,11 +99,11 @@ M5 (retail sales). All results are out-of-sample.
81
 
82
  | Plan | Monthly Credits | Rate Limit | Price |
83
  |------|----------------|------------|-------|
84
- | BASIC | 100 | 10 req/min | $0 |
85
- | PRO | 10,000 | 30 req/min | $49 |
86
- | ULTRA | 50,000 | 100 req/min | $199 |
87
- | MEGA | 200,000 | 300 req/min | $499 |
88
 
89
  ## License
90
 
91
- MIT — see [LICENSE](./LICENSE)
 
44
  # [171.2, 174.5, 177.8, 181.0, 184.3, 187.6, 190.8]
45
  ```
46
 
47
+ ## Use Cases
48
+
49
+ ![Retail demand forecast — 14-day ahead with 80% and 95% confidence intervals](https://huggingface.co/Eymdeyy/tsfa-forecasting-api/resolve/main/images/01_retail_forecast.png)
50
+ *Retail demand forecast — 14-day ahead with 80% and 95% confidence intervals*
51
+
52
+ ![EUR/USD exchange rate forecast — 30-day ahead with 95% probability band](https://huggingface.co/Eymdeyy/tsfa-forecasting-api/resolve/main/images/02_financial_forecast.png)
53
+ *EUR/USD exchange rate forecast — 30-day ahead with 95% probability band*
54
+
55
+ ![Energy consumption forecast — 48h ahead (ETT-h1 real data)](https://huggingface.co/Eymdeyy/tsfa-forecasting-api/resolve/main/images/03_energy_forecast.png)
56
+ *Energy consumption forecast — 48h ahead (ETT-h1 real data)*
57
+
58
+
59
  ## Models
60
 
61
  | Model | Credits | Best For |
 
72
  | Dataset | Model | Horizon | MAE | RMSE | MAPE | sMAPE |
73
  |---------|-------|---------|-----|------|------|-------|
74
  | ett_h1 | arima | 24 | 2.4524 | 2.9405 | 10.12% | 10.74% |
75
+ | ett_h1 | naive | 24 | 2.4524 | 2.9405 | 10.12% | 10.74% |
76
+ | ett_h1 | seasonal_naive | 24 | 1.9263 | 2.2837 | 8.25% | 8.74% |
77
  | exchange_rate | arima | 30 | 0.0085 | 0.0100 | 1.13% | 1.13% |
78
+ | exchange_rate | naive | 30 | 0.0085 | 0.0100 | 1.13% | 1.13% |
79
+ | exchange_rate | seasonal_naive | 30 | 0.0103 | 0.0117 | 1.37% | 1.37% |
80
  | m5_sample | arima | 14 | 9.0427 | 10.5617 | 7.63% | 7.43% |
81
+ | m5_sample | naive | 14 | 14.3541 | 16.7054 | 11.45% | 11.74% |
82
+ | m5_sample | seasonal_naive | 14 | 5.0372 | 6.2019 | 4.24% | 4.18% |
83
 
84
  Datasets: ETT-h1 (electricity transformer temperature), Exchange Rate (8 currencies),
85
  M5 (retail sales). All results are out-of-sample.
 
99
 
100
  | Plan | Monthly Credits | Rate Limit | Price |
101
  |------|----------------|------------|-------|
102
+ | Free | 500 | 10 req/min | $0 |
103
+ | Basic | 10,000 | 30 req/min | $49 |
104
+ | Pro | 50,000 | 100 req/min | $199 |
105
+ | Ultra | 200,000 | 300 req/min | $499 |
106
 
107
  ## License
108
 
109
+ MIT — see [GitHub](https://github.com/Eymdey/tsfa)