Content-Based Recommendations: Implementation on iOS and Android

Imagine you launch a news app with thousands of articles, but new users have no reading history. You need to show relevant content without data from others. Content-Based Filtering (based on attributes) solves this from day one. We analyze each article’s metadata—tags, categories, authors, text—and build a user profile based on what they interact with. For privacy-sensitive apps, CB can run entirely on-device without sending data to the server. This is especially relevant for financial or medical apps. In this article, we break down the key components of a CB system: from embeddings to on-device recommendations, with code examples for iOS and Python. On-device CB reduces cloud computing costs to ~$1000 per month. For a catalog of 10,000 items with 384-dimensional embeddings, the index is only ~15 MB. The user profile weighs 1.2 KB — recommendations are computed in 5 ms on an iPhone 12.

When is Content-Based better than Collaborative Filtering?

Three scenarios where CB is preferable:

• Niche content with rich metadata. Articles, recipes, travel routes — each item has a rich set of attributes (tags, categories, authors, locations). CF relies on the signal “users are similar”, but for niche content there may be too few such users, especially at launch.

• Privacy-first architecture. CB can run entirely on-device — the user profile is stored locally, recommendations are built without sending data to the server. This is critical for apps handling sensitive data.

• Long tail of content. A new article published an hour ago has no interaction history for CF. CB recommends it immediately once metadata is indexed.

How does on-device CB reduce costs?

On-device CB eliminates server-side computation. For a catalog of 10,000 items with 384-dimensional embeddings, the index takes ~15 MB. The user profile is 1.2 KB. Recommendations are computed in 5 ms on an iPhone 12. Average savings on cloud computing after adopting on-device CB are around $500–$1000 per month for a 10,000-item catalog. Data privacy is automatically ensured.

How does Content-Based work on-device?

For small catalogs (up to 50K items), the entire CB search can be moved to the device. The user profile is stored in UserDefaults, content embeddings are loaded on app start (JSON ~20 MB for 50K items × 384d float32). Recommendations are computed locally — no network requests, no latency.

class OnDeviceRecommender {
    private let userProfileKey = "user_embedding_v2"
    private var itemIndex: [(id: String, embedding: [Float])] = []

    func loadItemIndex(from url: URL) {
        let data = try! Data(contentsOf: url)
        itemIndex = try! JSONDecoder().decode([(id: String, embedding: [Float])].self, from: data)
    }

    func getRecommendations(count: Int) -> [String] {
        guard let profileData = UserDefaults.standard.data(forKey: userProfileKey),
              let profile = try? JSONDecoder().decode([Float].self, from: profileData)
        else { return popularItemIds(count: count) }

        return itemIndex
            .map { item in (item.id, cosineSimilarity(profile, item.embedding)) }
            .sorted { $0.1 > $1.1 }
            .prefix(count)
            .map { $0.0 }
    }

    private func cosineSimilarity(_ a: [Float], _ b: [Float]) -> Float {
        zip(a, b).map(*).reduce(0, +)
    }
}

Embeddings in the index are updated on start or on a schedule. We use precomputed vectors from the server, which minimizes device load.

Core system: TF-IDF and text embeddings

For articles, descriptions, news — two approaches: TF-IDF for speed, sentence embeddings for quality. In practice, we use sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 — 278 MB, supports Russian. Each item becomes a 384-dimensional vector. According to TF-IDF, word frequency and inverse document frequency provide a simple but effective relevance measure.

from sentence_transformers import SentenceTransformer

model = SentenceTransformer('paraphrase-multilingual-MiniLM-L12-v2')

def embed_article(article: Article) -> np.ndarray:
    text = f"{article.title}. {article.description}. {' '.join(article.tags)}"
    return model.encode(text, normalize_embeddings=True)

def similarity(v1: np.ndarray, v2: np.ndarray) -> float:
    return float(np.dot(v1, v2))

User profile — moving average

The user profile is a weighted average of the embeddings of content they interacted with. Recent interactions weigh more (exponential decay with coefficient 0.9):

def update_user_profile(profile: np.ndarray, new_item_embedding: np.ndarray,
                         interaction_weight: float, decay: float = 0.9) -> np.ndarray:
    updated = decay * profile + (1 - decay) * interaction_weight * new_item_embedding
    return updated / np.linalg.norm(updated)

Structured metadata: not just text

For product catalogs, text embeddings are supplemented with categorical features: category, brand, price range, color. The final vector is a concatenation of a normalized text embedding and one-hot/ordinal features with weights 0.7 and 0.3 respectively:

def build_item_vector(item: Product) -> np.ndarray:
    text_emb = embed_text(f"{item.name} {item.description}")
    cat_features = encode_categorical({
        'category': item.category_id,
        'brand': item.brand_id,
        'price_range': bucket_price(item.price)
    })
    return np.concatenate([text_emb * 0.7, cat_features * 0.3])

Comparison: Content-Based vs Collaborative

How to implement on-device CB on Swift: step-by-step

1. Content indexing. On the server, compute embeddings for each item using sentence-transformers. Save to a JSON file with fields id and embedding.
2. Index loading. On app launch, load the JSON into the OnDeviceRecommender array. For speed, use a binary format.
3. Collect interactions. Each time a user opens or likes content, save the item embedding in UserDefaults with a timestamp.
4. Update profile. On each interaction, recompute the moving average with exponential decay.
5. Generate recommendations. Call getRecommendations when displaying the feed or in the background.

What is included in the work

We provide:

• Analysis of content structure and available metadata
• Selection of the optimal embedding model for language and domain
• Building the index and profile update mechanism
• Implementation of on-device or server-side solution
• Integration with existing backend
• Documentation and team training

Our experience: over 10 years in mobile development, 30+ projects with AI recommendations. Guaranteed support after deployment. Contact us for a project evaluation — we will select the optimal architecture for your case. Order the development of a recommendation system for your project.

Time estimates

Get a consultation: tell us about your content and user scenarios, and we will propose a solution.

Machine Learning in Mobile Apps: CoreML, TFLite, and On-Device Models

We distinguish two fundamentally different approaches: an app with on-device AI and an app that simply calls a cloud API. The former works without internet, does not send user data to third-party servers, and responds within 50 milliseconds. The latter depends on network latency and pricing plans. Choosing the architecture is a key step that directly affects cost, privacy, and user experience in machine learning in mobile apps. Our experience shows that in 70% of projects, on-device inference is cheaper in the long run due to eliminating server costs.

How to Choose Between CoreML and TFLite for On-Device Inference?

CoreML — Apple's native framework for running ML models on device. Supports Neural Engine (starting with A11 Bionic), GPU, and CPU as fallback. Models are converted to .mlmodel format via coremltools from PyTorch, ONNX, or TensorFlow. Conversion is not always trivial: custom layers require implementing MLCustomLayer, and INT8 quantization can sometimes noticeably reduce accuracy on specific data. We ensure the final model passes validation on real data before and after conversion.

TensorFlow Lite — cross-platform alternative for Android and Flutter. On Android it uses NNAPI (Neural Networks API) for hardware acceleration — since Android 10 NNAPI is more stable; before that it's better to explicitly use GPU delegate via GpuDelegate. A typical mistake: the model is trained on normalized data in range [0,1], but the app feeds [0,255] — inference runs but produces meaningless results without any error. We include an automatic input data validation module in the SDK.

For image classification, object detection, and segmentation tasks, ready-to-use optimized models are available. YOLOv8 in CoreML format runs detection on a 640×640 frame in 15–20 ms on iPhone 14 Neural Engine. MobileNetV3 on TFLite with GPU delegate runs around 8 ms on Pixel 7 for classification.

What If You Need Text Generation On-Device?

Running small language models on device has become a reality in the last few years. Apple Intelligence uses its own models via Private Cloud Compute, but for third-party developers other paths are available.

llama.cpp with Metal backend on iOS is a working approach for phi-3-mini (3.8B parameters, 4-bit quantization, ~2.3 GB). Inference: 15–25 tokens/second on iPhone 15 Pro. For integration in Swift, use the Swift Package llama.swift or a wrapper via C interface llama.h. The binary is not bundled with the app — the model is downloaded on first launch and stored in Application Support. Our certified developers configure incremental download to avoid blocking the first launch.

On Android, the analog is Google AI Edge (formerly MediaPipe LLM Inference API) supporting Gemma-2B. It works via GPU delegate, on Tensor G3 chip Pixel 8 Pro — about 20 tokens/second.

Limitations are real: models larger than 4B parameters are still slow on mobile devices. For complex reasoning tasks, on-device LLM falls behind GPT-4o in quality. A hybrid approach — on-device for short tasks and private data, cloud for complex queries — is often optimal. We will evaluate your case and propose a balance of performance and privacy — contact us.

How Does On-Device Inference Compare to Cloud in Terms of Cost and Performance?

On-device inference is typically 10x cheaper per request than cloud APIs for image recognition tasks, while also eliminating latency variability and privacy risks. The table below summarizes the trade-offs.

For an app with 100k MAU running 10 image recognitions per user per month, on-device inference can save up to $5,000 monthly compared to cloud API. Get a free consultation on your ML architecture today.

Integrating OpenAI API and Other Cloud Models

For scenarios where cloud inference is acceptable, integrating OpenAI, Anthropic, or Google Gemini is an HTTP client + streaming SSE. In Swift, AsyncThrowingStream is convenient for streaming responses. In Kotlin, use Flow.

Critically: API keys must never be stored in the app bundle. Even an obfuscated key can be extracted from the IPA in 10 minutes using strings or frida. Correct architecture: mobile app → your own backend → OpenAI API. The backend controls rate limiting, logs requests, and protects the key.

What Is Included in the Work (Deliverables)

• Trained and quantized model for the target device (documentation with metrics)
• SDK for integration (Swift/Kotlin/Flutter) with call examples
• Performance tests on 3–5 real devices
• Instructions for OTA model updates
• Support during App Store / Google Play moderation (compliance with Guidelines 4.2, 5.1)
• 2 weeks of technical support after release

Typical Project Pipeline

1. Task analysis — measure latency, privacy, size, supported devices.
2. Model prototyping — in Python, evaluate accuracy on target data.
3. Conversion and quantization — for CoreML/TFLite with validation.
4. Integration into the app — model wrapped in a service layer (easy to swap CoreML ↔ TFLite ↔ cloud).
5. Testing — on real devices, measure FPS, RAM, battery.
6. Deployment — via TestFlight / Firebase App Distribution, monitor metrics.

Timelines: integration of a ready CoreML/TFLite model — 1–2 weeks, development of a custom model with mobile optimization — from 6 weeks, on-device LLM chat with personalization — 4–8 weeks.

Why We Take on Complex Cases?

10+ years of experience in mobile development, 50+ implemented AI/ML solutions, guarantee of compatibility with current iOS and Android versions. All projects undergo code review and load testing. The cost includes preparation of moderation documentation and training of your team.

Contact us — we will help you choose the architecture and implement ML in your app turnkey. Order an audit of your existing solution — we will assess the potential for server cost savings free of charge. In some projects, savings can reach significant amounts per month.