A data scientist is developing a machine learning model to predict housing prices based on various features, such as location, size, and age of the property. After testing the model, she notices that small changes in the size of the house lead to large fluctuations in predicted prices. What does this indicate about the sensitivity of the predictor used in her model?

The fact that tiny changes in house size cause big swings in the predicted price shows that the size predictor is highly sensitive in the model. This means the model’s coefficient for size is large, so even a small input shift leads to a large output change. Such high sensitivity often signals over‑fitting or a lack of regularization, making the model unstable to small data variations. For instance, if a 10‑square‑meter increase suddenly raises the predicted price by $50,000, the model is reacting too strongly to that feature. To improve stability, the data scientist might reduce the coefficient’s influence through regularization or by transforming the feature.