Implement **ensemble averaging** to combine predictions from multiple ML models into one final prediction. You’ll take a list of per-model predictions and return the averaged prediction, which is a simple but common baseline for improving stability.

Ensemble averaging is defined as:
$$
\hat{y} = \frac{1}{M}\sum_{m=1}^{M}\hat{y}^{(m)}
$$

## Requirements

Implement the function
```python
def ensemble_average(predictions):
    \"""
    Computes the element-wise average of predictions from multiple models.

    Args:
        predictions (np.ndarray): A 2D array of model predictions, where
            predictions[m][i] is the prediction of model m for item i.

    Returns:
        np.ndarray: The averaged prediction for each item.
    \"""
    # Your solution below
```

**Rules:**
- Compute the element-wise mean across models (average over the first dimension).
- Return a NumPy array of floats with the same length as a single model’s prediction list.
- Do not use any prebuilt ensembling utilities (e.g., from scikit-learn).
- Use NumPy for the numeric computation.
- Keep it as a single Python function.

## Example

```python
predictions = np.array([
    [0.2, 0.8, 0.4],  # model 1
    [0.1, 0.9, 0.6],  # model 2
    [0.3, 0.7, 0.5],  # model 3
])

ensemble_average(predictions)
```

Output:
```python
array([0.2, 0.8, 0.5])
```

Flatten Nested List Iterator

Can Place Flowers

Ensemble averaging

Solve this easy level ML coding question from General. The premier LeetCode for ML platform to master Python, SQL, and Machine Learning algorithms.

1229. Ensemble averaging

Examples

Constraints

Similar Questions