{"id":8051,"date":"2021-01-07T01:05:54","date_gmt":"2021-01-07T09:05:54","guid":{"rendered":"https:\/\/www.couchbase.com\/blog\/?p=8051"},"modified":"2025-06-13T20:08:50","modified_gmt":"2025-06-14T03:08:50","slug":"machine-learning-predictions-couchbase-lite-predictive-query","status":"publish","type":"post","link":"https:\/\/www.couchbase.com\/blog\/machine-learning-predictions-couchbase-lite-predictive-query\/","title":{"rendered":"Make Machine Learning Predictions With Couchbase Lite"},"content":{"rendered":"

Couchbase Lite\u2019s Predictive Query API<\/a> allows applications to leverage pre-trained, Machine Learning(ML) models to run predictive queries against data in embedded Couchbase Lite database in a convenient, fast and always-available way. These predictions can be combined with predictions made against real-time data captured by your app to enable a range of compelling applications. The Predictive Query API in Couchbase Lite is the first of its kind in an embedded database. We had announced<\/a> the Developer Preview version of Predictive Query API with Couchbase Mobile 2.5 last year. With Couchbase Mobile 2.7<\/a>, we are happy to announce the General Availability of this feature.<\/p>\n

In this post, we provide an overview of the feature including context around why we built it and the kinds of applications that it <\/ins>can enable. We also demonstrate the use of the Predictive API with an example. You can refer to the documentation<\/a> pages for specifics on the API and sample code snippets.<\/p>\n

Machine Learning on Mobile – Motivation<\/h2>\n

Machine Learning has been traditionally been done in the cloud. With access to \u201cunbounded\u201d compute and storage resources, it seemed like the only viable place to do it. While that may be true for certain applications, there are a number of reasons to perform machine learning locally on mobile device.<\/p>\n

Fast & Responsive<\/h3>\n

By avoiding the round trip time to the cloud, the response times to predictions can be guaranteed to be in order of a few milliseconds regardless of state of network connection. This is important as the responsiveness of an app is directly correlated to the end user experience which is important for app retention.<\/p>\n

Always Available<\/h3>\n

By running machine learning locally on device, you can make predictions even in disconnected state. Your application and your data is always available. This is particularly relevant in case of field applications deployed in disconnected environments.<\/p>\n

Data Privacy<\/h3>\n

Running predictions locally on the device implies that sensitive data does not have to ever leave your device. You can use this to build apps with highly personalized experiences without compromising on data privacy restrictions.<\/p>\n

Bandwidth Savings<\/h3>\n

By avoiding the need for data to be transferred to the cloud, you can save on bandwidth costs. This is particularly important in case of network bandwidth constrained environments where data plans come at a premium.<\/p>\n

All of the abovementioned benefits align well with the paradigm of edge computing<\/a> where there is a growing need to bring storage and compute closer to the edge.<\/p>\n

Mobile ML – Ecosystem<\/h2>\n

Mobile ML is a reality and there are several ecosystem enablers that make that possible.<\/p>\n

Powerful Mobile Devices<\/h3>\n

Mobile devices are getting to be incredibly powerful. For instance, the recently launched iPhone11<\/a> and Pixel 4<\/a> include dedicated neural core engines. Innovation at the silicon layer make it feasible to run ML models locally on mobile devices. By taking advantage of platform hardware acceleration capabilities, the models can run in a performant manner.<\/p>\n

Mobile Optimized Models<\/h3>\n

Machine Learning models have traditionally been strorage and compute intensive. There are several efforts\/projects underway to optimize the models for resource utilization while maintaining required level of accuracy. There is a growing network of open-source pre-trained ML models such as MobileNet<\/a> and SqueezeNet<\/a> that are optimized to run on mobile devices.<\/p>\n

Machine Learning Frameworks<\/h3>\n

All the major mobile platforms include support for Machine Learning frameworks and libraries that make it extremely easy for developers to integrate ML support into their apps. These frameworks leverage hardware acceleration and low level APIs that make it very performant. Examples include Core ML<\/a> for iOS, Tensorflow lite<\/a> for Android, ML.NET<\/a> for Windows and ML Kit<\/a> among others.<\/p>\n

Creating ML Models<\/h3>\n

There is a growing number of open source tools and platforms such as TensorFlow<\/a> and createML<\/a> that make it easier than ever to create machine learning models. You don\u2019t need to be a data scientist to create one.<\/p>\n

Predictive Query API<\/h2>\n

Predictive Queries API enable mobile apps to leverage pre-trained machine learning(ML) models to make predictions on Couchbase Lite data. The API can be used to combine real-time predictions made on data input into the app in real-time with predictions on app data stored in Couchbase Lite.<\/p>\n

By building prediction index<\/a> during write time, users can get see significant improvements in performance of their queries. The prediction results can be materialized in Couchbase Lite and synced over to other clients via Sync Gateway<\/a>.<\/p>\n

Applications<\/h3>\n

There are several applications of Machine Learning on mobile including image classifications, voice recognition, object recognition and content-based recommender systems. Combining those predications with data that is stored in Couchbase Lite has the potential to revolutionalize day-to-day activities across several industries. All these applications benefit from running the machine learning locally viz., guaranteed high availability, faster response, efficient network bandwidth usage and data privacy. Here are a few examples-<\/p>\n

Retail & e-commerce<\/h4>\n

Consider this workflow
\n– You walk into a store with a photo of an item of interest. For instance, a photo of a handbag that you saw on someone.
\n– You walk up to the sales clerk to enquire if the item is available.
\n– The sales clerk takes a photo of the item with his tablet that is running a catalog \/ inventory app
\n– The captured image is used to search the store catalog database to determine it\u2019s availability.
\n– If it\u2019s available in the store you are directed to the right aisle. You can also be presented with alternatives and recommendations on other related items.<\/p>\n

\"Machine<\/figure>\n

Image based search augment the more traditional text-based search and even voice-based search experience which rely on the user\u2019s ability to describe the item of interest. Applications with image based search can significantly improve both the online and in-store shopping experience. While the advantages of image based search are quite obvious in case of ecommerce applications, workflows such as the one described above provides an opportunity for traditional brick-and-motor stores to compete with online shopping experiences.<\/p>\n

Behind the scenes, the catalog\/inventory app uses an Image Classifier ML model to identify the item that is captured using the tablet camera. Once identified, the app looks up the local Couchbase Lite database to check if the item is available at the store and retrieves other relevant details such as if it is in stock and the aisle where it can be found. The images never leave the store app and can be locally deleted after use, alleviating any privacy concerns.<\/p>\n

Hospitality<\/h4>\n

Consider a self-ordering kiosk at a fast food restaurant. Here is a typical workflow.
\n– You walk up to the kiosk equipped with a camera that captures your image (you have to opt in )
\n– The captured face image is used to lookup the database of registered patrons to identify your preferences
\n– The system can pull up order history, suggest meal orders, apply loyalty points and such. Your order can be placed using credit card info on file.<\/p>\n

\"Machine<\/figure>\n

Self-ordering kiosks are fairly ubiquitous and have revolutionized the meal ordering experience by reducing wait times resulting in faster service. Equipping these kiosks with facial recognition technology can make that experience even more seamless and faster.<\/p>\n

Behind the scenes, the kiosk is running an app that uses a Facial Recognition ML model such as OpenFace<\/a> to generate a unique fingerprint of the captured face image. The app then performs a similarity match<\/em> between the fingerprint of the captured face image and the fingerprints of images in Couchbase Lite database to identify the closest match.<\/p>\n

Feature Walkthrough<\/h3>\n

The best way to understand how the API works is through an example. In this post, I am going to describe how you can implement Facial Recognition application discussed above using the Predictive Query API. This is probably the more complicated workflow. The image based search app using classifier model follows a similar pattern except that it is a lot simpler.<\/p>\n