To predict a time series with deep learning in Keras, first define the value to forecast, how far ahead to predict, the sampling cadence, and which past observations and features are available. Then create chronological input windows paired with their future targets, train a model such as an LSTM, and evaluate predictions on later data the model did not train on. Keras’s time-series examples show workable approaches; they do not establish one architecture as best for every forecasting problem.
Define the forecast before choosing a model
A model cannot be evaluated meaningfully until its prediction task is specific. Write down the following before preparing data:
- Target: the value to predict, such as temperature or road-segment speed.
- Horizon: how far into the future each prediction reaches. A prediction for the next time step is a different task from a prediction several steps ahead.
- Cadence: the interval between observations, such as every 10 minutes or once per day.
- Inputs: whether the model receives only the target’s history or additional features, such as humidity and pressure.
- Series structure: whether the data is one sequence or many related sequences, such as measurements from connected road segments.
- Output: one future value or a sequence of future values.
These choices determine how input windows and targets must line up, and what counts as a useful validation result. A model that performs well for one horizon or data split may not perform well for another.
Prepare chronological data and align windows with targets
Keep observations in time order. For a realistic estimate of future forecasting performance, reserve later observations for validation rather than randomly mixing past and future samples. Randomly shuffling time points can let information from the future influence training and make evaluation less representative of deployment.
Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Scan for outdated or missing drivers - takes under a minute3Clear out junk files and repair common Windows errors#1 Best Overall
- Read Before You Buy — No Video Output: These adapters support charging and USB 2.0 data transfer, but cannot transmit video signals. Except for standard USB webcams (which use USB data only), they are not compatible with HDMI/DisplayPort cables, video-capable USB-C hubs, or docking stations with video output.
- Convert USB-A Ports to USB-C: Designed to connect USB-C earphones, cables, flash drives, card readers, and other USB-C accessories to standard USB-A ports. Plug-and-play with no drivers or software required.
- Aluminum Alloy Housing: Built with a sturdy aluminum alloy shell that aids in heat dissipation and protects against daily wear and scratches. Designed to maintain a stable and secure connection.
- Compact & Travel-Friendly: The ultra-compact design allows the adapter to stay plugged into your device without blocking adjacent ports or adding bulk, reducing wear and tear on your original USB ports.
- 12-Month Warranty: Backed by a 12-month manufacturer warranty for peace of mind. Designed to meet strict quality control standards for reliable everyday performance.
Before making windows, check that timestamps and observations are usable for the cadence you intend to model. Handle missing, duplicated, or invalid values deliberately; the Keras windowing utility does not replace these data-cleaning decisions. Its documented input is a sequence of consecutive data points, with the time dimension on axis 0.
Keras’s timeseries_dataset_from_array API creates sliding windows. Sequence length sets the number of observations in each window, while stride and sampling rate control how windows move through or sample the sequence. Targets correspond to the window that starts at the same index.
Rank #2
- 5-in-1 USB-C Hub: Experience comprehensive connectivity featuring a Power Delivery input, two USB-A 2.0 ports, a USB-A 3.0 port, and an HDMI port. (Note: The USB-C power delivery input port is only for connecting an external wall charger to power your laptop and cannot power peripheral devices.)
- 90W Pass-Through Charging: Achieve optimal charging with 90W pass-through power to your laptop, supported by a total input of 100W, with the hub reserving 10W for operational efficiency. (Note: Wall charger not included.)
- Quick Data Transfers: Accelerate your productivity with rapid data transfers using a high-speed 5Gbps USB 3.0 port and two 480Mbps USB 2.0 ports.
- 4K HDMI Display: Enhance your visual experience with a hub capable of delivering 4K resolution at 30Hz in both mirror and extend modes. Please note that this hub is compatible with MacBook (macOS 12 and newer), Windows 10 and 11, ChromeOS, and laptops equipped with DP Alt Mode and Power Delivery. Note: This device is not compatible with Linux.
- What You Get: Anker USB-C Hub (5-in-1, 4K HDMI), welcome guide, 18-month warranty, and our friendly customer service.
For example, if a window contains observations 0 through 9 and should predict observation 10, the target paired with the window starting at index 0 must be observation 10. An off-by-one target alignment can train a model on the wrong forecasting task even when the code runs without errors.
Start with an LSTM example, not an assumed winner
Keras’s weather forecasting example demonstrates a practical LSTM workflow. It uses the Jena Climate dataset from the Max Planck Institute for Biogeochemistry in Germany: 14 features, including temperature, pressure, and humidity, sampled every 10 minutes from January 10, 2009 through December 31, 2016. Those figures describe that tutorial dataset, not a general requirement for forecasting.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Rank #3
- Sleek 7-in-1 USB-C Hub: Features an HDMI port, two USB-A 3.0 ports, and a USB-C data port, each providing 5Gbps transfer speeds. It also includes a USB-C PD input port for charging up to 100W and dual SD and TF card slots, all in a compact design.
- Flawless 4K@60Hz Video with HDMI: Delivers exceptional clarity and smoothness with its 4K@60Hz HDMI port, making it ideal for high-definition presentations and entertainment. (Note: Only the HDMI port supports video projection; the USB-C port is for data transfer only.)
- Double Up on Efficiency: The two USB-A 3.0 ports and a USB-C port support a fast 5Gbps data rate, significantly boosting your transfer speeds and improving productivity.
- Fast and Reliable 85W Charging: Offers high-capacity, speedy charging for laptops up to 85W, so you spend less time tethered to an outlet and more time being productive.
- What You Get: Anker USB-C Hub (7-in-1), welcome guide, 18-month warranty, and our friendly customer service.
In the example, an LSTM consumes a history window and predicts a temperature value. The notebook creates training and validation data, uses the windowing utility, trains with Adam and mean squared error, and monitors validation loss. It also uses ModelCheckpoint and EarlyStopping. This is a useful pattern to adapt, but it is not evidence that an LSTM will outperform other models on your data.
Choose an architecture that matches the data structure
| Approach | Data structure and task | What the Keras example demonstrates |
|---|---|---|
| LSTM | Features observed over time; predict a future value. | The weather notebook uses an LSTM to forecast temperature from a history window. See Keras weather forecasting. |
| Graph convolution plus LSTM | Multiple spatially related series, where a graph represents relationships among locations or segments; predict future values. | The traffic notebook models road-segment relationships and forecasts speed. It uses PeMSD7 data from stations in California’s District 7 during weekdays in May and June 2012. See Keras traffic forecasting. |
| Transformer time-series classifier | Time-series inputs mapped to class labels rather than future numeric values. | This is a classification example, not a forecasting tutorial. See Keras Transformer classification. |
If you have separate measurements for related locations, fitting a wholly independent model to each can ignore information shared by neighboring locations. Keras’s traffic example represents roads as a graph and combines graph convolution with an LSTM to incorporate those relationships. Whether that additional structure helps your use case must be established by validation on your own data.
Rank #4
- Dual Converters, Infinite Potential：Includes 2× USB C male to USB A female adapters and 2× USB A male to USB C female adapters. Perfect for a wide range of uses—tablets with Bluetooth keyboards, expand USB ports on macbook, and more. Two different converters for all your daily needs
- Next-Level 10Gbps & 3A Charging: No more slow 480Mbps, this usb to usb c adapter has a transfer speed of up to 10Gbps, allowing you to do more transferring in less time. This usb adapter fits both USB A and USB C charger, supporting up to 3A fast charging
- Upgraded Exquisite Craftsmanship: With an aluminum alloy housing and metal connector, the usbc to usb adapter is extremely durable and sturdy. Rigorously tested to withstand more than 10,000 times of plugging and unplugging, ensuring long-lasting performance
- Broad Compatible: The usb c to usb adapter widely supports all USB C/ USB A devices like laptops, tablets, cellphones, car chargers, and phone chargers. Such as compatible with MacBook Pro/Air 2023/2022, Thunderbolt 4/3 Devices,Apple MagSafe Watch 9/8/7/SE/Ultra, iPad Pro 2022/2021, Samsung Galaxy S23/S20/S10, and iPhone 17/16/15 Pro. Plug and play
- Please Note: To reach 10Gbps speed, keep the cable under 3.3 ft. For USB A Male to USB C adapters, try flipping the USB C connector. USB C Male to USB A adapters support bidirectional 10Gbps transfer within 3.3 ft
The Transformer notebook belongs to a different task: classification. It processes time-series data shaped as batch, sequence length, and features through attention-based encoder blocks, then predicts class labels. Its presence alongside forecasting examples in the Keras time-series examples index does not make its output a future-value forecast.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Train and evaluate against later observations
Use validation data that reflects the future predictions you ultimately need to make. Evaluate the chosen horizon and output format, and select metrics suited to the target and practical cost of forecast errors; the Keras examples do not establish a universal accuracy threshold or universally correct metric.
Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minuteWindows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallBest Value
- 5-in-1 Connectivity: Equipped with a 4K HDMI port, a 5 Gbps USB-C data port, two 5 Gbps USB-A ports, and a USB C 100W PD-IN port. Note: The USB C 100W PD-IN port supports only charging and does not support data transfer devices such as headphones or speakers.
- Powerful Pass-Through Charging: Supports up to 85W pass-through charging so you can power up your laptop while you use the hub. Note: Pass-through charging requires a charger (not included). Note: To achieve full power for iPad, we recommend using a 45W wall charger.
- Transfer Files in Seconds: Move files to and from your laptop at speeds of up to 5 Gbps via the USB-C and USB-A data ports. Note: The USB C 5Gbps Data port does not support video output.
- HD Display: Connect to the HDMI port to stream or mirror content to an external monitor in resolutions of up to 4K@30Hz. Note: The USB-C ports do not support video output.
- What You Get: Anker 332 USB-C Hub (5-in-1), welcome guide, our worry-free 18-month warranty, and friendly customer service.
During training, inspect validation behavior rather than relying on training loss alone. The weather example uses validation loss with EarlyStopping and ModelCheckpoint, then demonstrates sample predictions. These techniques can help stop training when validation no longer improves and preserve a useful model checkpoint.
- Build the input windows and aligned future targets. Verify at least one window and target by hand against their timestamps.
- Fit the model on the earlier portion of the timeline. Keep the later validation period separate from model fitting.
- Monitor validation performance. Use a checkpoint and early stopping if appropriate for your training workflow.
- Plot predictions against actual values. Check timestamp alignment as well as error: a shifted prediction can look plausible while answering the wrong question.
- Compare alternatives on the same split and horizon. Assess validation performance and the computation required in your setting; the official examples are not a controlled head-to-head benchmark.
Choose a Keras backend and execution environment
Keras 3 lists JAX, TensorFlow, and PyTorch as backend choices in its getting started documentation. Follow the current setup instructions for the backend you select, and check the relevant Keras developer guides for implementation details.
The Keras code examples page describes notebook examples that can run in Google Colab with hosted GPU and TPU runtimes. A hosted accelerator is an option, not a prerequisite for every dataset. The useful execution setup depends on model size, data volume, backend compatibility, and the workload you actually need to run.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
