Time series with RNN in TensorFlow - Model Metrics & Evaluation

Metrics & Evaluation - Time series with RNN

Which metric matters for Time series with RNN and WHY

For time series prediction using RNNs, common metrics include Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). These measure how close the predicted values are to the actual values. Lower values mean better predictions.

When the task is classification on time series data, metrics like accuracy, precision, recall, and F1 score become important.

Choosing the right metric depends on the goal: for continuous value prediction, use error metrics; for classification, use classification metrics.

Confusion matrix example for time series classification

    Actual \ Predicted | Positive | Negative
    -------------------|----------|---------
    Positive           |    50    |   10
    Negative           |    5     |   35

    Total samples = 50 + 10 + 5 + 35 = 100
    

From this matrix:

• True Positives (TP) = 50
• False Positives (FP) = 5
• True Negatives (TN) = 35
• False Negatives (FN) = 10

Precision = TP / (TP + FP) = 50 / (50 + 5) = 0.91

Recall = TP / (TP + FN) = 50 / (50 + 10) = 0.83

F1 Score = 2 * (Precision * Recall) / (Precision + Recall) ≈ 0.87

Precision vs Recall tradeoff with examples

In time series classification, sometimes you want to catch all positive events (high recall), even if some false alarms happen (lower precision). For example, detecting machine failures early.

Other times, you want to be very sure when you predict a positive (high precision), like in medical diagnosis from time series data.

Improving one often lowers the other. You must decide which is more important for your use case.

What "good" vs "bad" metric values look like for time series with RNN

For regression tasks:

• Good: RMSE close to 0 means predictions are very close to actual values.
• Bad: High RMSE means large errors in prediction.

For classification tasks:

• Good: Precision and recall above 0.8 show reliable detection.
• Bad: Precision or recall below 0.5 means many mistakes or missed events.

Common pitfalls in metrics for time series with RNN

• Ignoring temporal order: Metrics should consider time dependencies, not just overall accuracy.
• Data leakage: Using future data in training inflates metrics falsely.
• Overfitting: Very low training error but high test error means model memorizes instead of learns.
• Accuracy paradox: High accuracy can be misleading if classes are imbalanced.

Self-check question

Your RNN model for time series classification has 98% accuracy but only 12% recall on the positive class (e.g., failure events). Is it good for production? Why or why not?

Answer: No, it is not good. The model misses 88% of positive events, which is dangerous if those events are critical. High accuracy is misleading because the dataset is likely imbalanced with many negatives. Improving recall is essential.

Key Result

For time series with RNN, use error metrics for prediction tasks and precision/recall for classification; watch for tradeoffs and data leakage.

Practice

1. What is the main purpose of using an RNN (Recurrent Neural Network) in time series prediction?

easy

A. To learn patterns from past time steps to predict future values

B. To classify images into categories

C. To reduce the size of the dataset

D. To perform arithmetic operations on numbers

Solution

1. Step 1: Understand RNN's role in time series

   RNNs are designed to process sequences by remembering past information.

2. Step 2: Connect RNN to prediction task

   They use past time steps to predict future values in a sequence.

3. Final Answer:

   To learn patterns from past time steps to predict future values -> Option A

4. Quick Check:

   RNN predicts future from past [OK]

Hint: RNNs remember past data to predict next steps [OK]

Common Mistakes:

• Confusing RNN with image classifiers
• Thinking RNN reduces data size
• Assuming RNN does simple math only

2. Which of the following is the correct way to add a SimpleRNN layer with 50 units in TensorFlow Keras?

easy

A. model.add(tf.keras.layers.SimpleRNN(input_shape=(None, 1), 50))

B. model.add(tf.keras.layers.RNN(50))

C. model.add(tf.keras.layers.SimpleRNN(activation='relu', 50))

D. model.add(tf.keras.layers.SimpleRNN(units=50))

Solution

1. Step 1: Recall SimpleRNN syntax

   The units parameter must be named or passed first as an integer.

2. Step 2: Check each option

   model.add(tf.keras.layers.SimpleRNN(units=50)) uses named parameter units=50, which is correct and clear.

3. Final Answer:

   model.add(tf.keras.layers.SimpleRNN(units=50)) -> Option D

4. Quick Check:

   Use named units parameter [OK]

Hint: Use named 'units' parameter for clarity [OK]

Common Mistakes:

• Passing activation before units
• Omitting units parameter name
• Missing input_shape when required

3. Given this code snippet, what will be the shape of the output from the SimpleRNN layer?

model = tf.keras.Sequential()
model.add(tf.keras.layers.SimpleRNN(10, input_shape=(5, 2)))
output = model(tf.random.uniform((3, 5, 2)))
print(output.shape)

medium

A. (3, 2, 10)

B. (3, 10)

C. (5, 10)

D. (3, 5, 10)

Solution

1. Step 1: Understand input and output shapes

   Input shape is (batch=3, time steps=5, features=2). SimpleRNN with 10 units outputs (batch, units) by default.

2. Step 2: Confirm output shape

   Since return_sequences is False by default, output shape is (3, 10).

3. Final Answer:

   (3, 10) -> Option B

4. Quick Check:

   Default SimpleRNN outputs last step shape [OK]

Hint: Default SimpleRNN outputs (batch, units) shape [OK]

Common Mistakes:

• Assuming output keeps time steps dimension
• Confusing batch size with time steps
• Misreading input_shape order

4. Identify the error in this TensorFlow RNN model code:

model = tf.keras.Sequential()
model.add(tf.keras.layers.SimpleRNN(20))
model.add(tf.keras.layers.Dense(1))
model.summary()
model.compile(optimizer='adam', loss='mse')
model.fit(x_train, y_train, epochs=5)

Assume x_train shape is (100, 10, 3).

medium

A. SimpleRNN layer missing input_shape parameter

B. Dense layer should have more units

C. Loss function 'mse' is invalid

D. Optimizer 'adam' is not supported

Solution

1. Step 1: Check input shape requirement

   First layer in Sequential must specify input_shape if no input layer is given.

2. Step 2: Verify code

   SimpleRNN(20) lacks input_shape=(10,3), so model won't know input dimensions.

3. Final Answer:

   SimpleRNN layer missing input_shape parameter -> Option A

4. Quick Check:

   First layer needs input_shape [OK]

Hint: Always specify input_shape in first RNN layer [OK]

Common Mistakes:

• Ignoring input_shape in first layer
• Changing Dense units unnecessarily
• Misunderstanding loss or optimizer names

5. You want to predict the next 3 values in a time series using an RNN. Which model setup is best to output a sequence of 3 predictions for each input sequence?

hard

A. Use SimpleRNN with return_sequences=True and a Dense layer with 3 units

B. Use SimpleRNN with return_sequences=False and a Dense layer with 3 units

C. Use SimpleRNN with return_sequences=True and a TimeDistributed Dense layer with 1 unit

D. Use SimpleRNN with return_sequences=False and a TimeDistributed Dense layer with 1 unit

Solution

1. Step 1: Understand output requirements

   Predicting next 3 values means outputting a sequence of length 3, one prediction per time step.

2. Step 2: Choose correct RNN and output layer

   return_sequences=True outputs a sequence (batch, time steps, units). A Dense layer with 3 units applied at each time step (via TimeDistributed) or a Dense layer with 3 units on the last step can be used depending on output shape.

3. Step 3: Analyze options

   Use SimpleRNN with return_sequences=True and a Dense layer with 3 units outputs only the last time step's output with 3 units, which is not a sequence of 3 predictions. Use SimpleRNN with return_sequences=True and a TimeDistributed Dense layer with 1 unit uses return_sequences=True and TimeDistributed Dense(1), producing a sequence output of shape (batch, time steps, 1), which can be adjusted to 3 time steps for 3 predictions.

4. Final Answer:

   Use SimpleRNN with return_sequences=True and a TimeDistributed Dense layer with 1 unit -> Option C

5. Quick Check:

   return_sequences=True + TimeDistributed Dense(1) outputs sequence predictions [OK]

Hint: return_sequences=True + TimeDistributed Dense(1) for sequence output [OK]

Common Mistakes:

• Using return_sequences=False for sequence output
• Using Dense without TimeDistributed for sequence output
• Misunderstanding output shapes