Getting accurate univariate forecasts shouldn’t require weeks of effort or a degree in machine learning. Whether it’s planning inventory, predicting energy output, or optimizing a supply chain, time series forecasting should be simple, scalable, and reliable.
That’s why we built Sulie: a foundation model designed to make forecasting easier, faster, and accessible to everyone.
🔎 What Is Sulie?
Sulie is a foundation model for time series forecasting. Trained on diverse datasets across industries and tasks, Sulie is industry-agnostic and data-flexible, making it capable of tackling a wide range of time series forecasting problems without requiring task-specific customization.
🥁 Why Sulie?
Here’s why Sulie stands out:
- Forecast in a Few Lines of Code - start forecasting quickly, without complex pipelines or setup.
- Auto Fine-Tuning - Sulie adapts to your data to improve accuracy while you stay focused on your goals.
- Zero ML Hassle - No need to train models, fiddle with hyperparameters or deal with infrastructure. Sulie takes care of the heavy lifting.
🔥 Real-World Use Cases
Sulie is perfect for:
- Energy - Predict renewable energy output, like wind or solar generation.
- Retail - Plan product restocking and forecast sales trends.
- Supply Chain - Optimize logistics and reduce inventory costs.
- Financial Data - Forecast trends in revenue or expenses.
📚 How It Works
Integrating Sulie into your workflow or SaaS is simple. Here’s an example:
import os
import pandas as pd
from sulie import Sulie
client = Sulie(
api_key=os.environ.get("SULIE_API_KEY")
)
# Prepare your data
df = pd.DataFrame(your_data)
# Upload a dataset
dataset = client.upload_dataset(
name="product-purchases-v1",
df=df
)
# Forecast on time-series data
forecast = client.forecast(
dataset="product-purchases-v1",
horizon=30, # 30 time steps ahead
target_col="y"
)
Get Started
Top comments (0)