"Gemma 4 Analyzed My Bank Statements – Apparently I 'Have a Problem' with Coffee and Late-Night Apps"

Abel Mhlanga — Fri, 22 May 2026 12:27:10 +0000

This is a submission for the Gemma 4 Challenge: Build with Gemma 4

What I Built

Bank statement Analyzer — upload 3–6 months of statements, get a breakdown of spending patterns, subscriptions you forgot about, anomalies, and concrete suggestions to cut your costs.

Demo

github-production-user-asset-6210df.s3.amazonaws.com

Code

AbelCodeCanvas / my-bank-app

Bank statement Analyzer — upload 3–6 months of statements, get a breakdown of spending patterns, subscriptions you forgot about, anomalies, and concrete suggestions to cut your costs.

markdown

💰 Bank Statement Analyser

Upload 3–6 months of bank statements and get a clear breakdown of:

📊 Spending patterns – where your money really goes
🔁 Subscriptions you forgot about – recurring charges you might not need
⚠️ Anomalies – unusual or unexpected transactions
✂️ Concrete suggestions – actionable advice to cut costs

📋 Prerequisites

Before you begin, make sure your local machine has:

Python 3.9 or higher (recommended: 3.10)
Git – to clone the repository
A Hugging Face account (free) with a User Access Token Create one here
At least 16 GB RAM (32 GB recommended)
GPU with 12+ GB VRAM (optional but strongly recommended for fast inference) – if no GPU, the app will fall back to CPU (very slow for 26B model)

Note: The 26B A4B model is large but uses Mixture‑of‑Experts to reduce compute…

View on GitHub

How I Used Gemma 4

For my Bank Statement Analyser, I used Gemma 4 26B A4B (the instruction-tuned variant) on Hugging Face. While not exactly one of the standard sizes (E2B, E4B, or 31B Dense), this 26B parameter model strikes an ideal balance for the task:

Long context handling – Bank statements over 3–6 months contain hundreds of transactions. The model’s large context window lets me feed entire statements without chunking, preserving temporal patterns.

Structured extraction – Gemma 4’s instruction-tuning excels at parsing semi-structured data (PDF/CSV statements) and outputting consistent JSON breakdowns of spending, subscriptions, and anomalies.

Reasoning for suggestions – The 26B size provides enough reasoning capacity to identify cost-cutting opportunities (e.g., duplicate subscriptions, high-fee accounts, irregular charges) without the latency or cost of a dense 31B model.

A4B efficiency – The Mixture-of-Experts (A4B) architecture reduces compute per token, making it feasible to run locally or on a free Hugging Face T4 GPU.

In short, Gemma 4 powers the entire pipeline: statement parsing → spending categorization → anomaly detection → actionable recommendations.

Abel MhlangaFollow

Software Engineer | Python, Odoo ERP, API Integrations | 10+ years backend dev & complex systems knowledge-sharing enthusiast.I design, deploy, and optimize web/mobile apps that drive business goals.

DEV Community: Abel Mhlanga

"Gemma 4 Analyzed My Bank Statements – Apparently I 'Have a Problem' with Coffee and Late-Night Apps"

What I Built

Demo

Code

AbelCodeCanvas / my-bank-app

Bank statement Analyzer — upload 3–6 months of statements, get a breakdown of spending patterns, subscriptions you forgot about, anomalies, and concrete suggestions to cut your costs.

💰 Bank Statement Analyser

📋 Prerequisites

How I Used Gemma 4

Abel MhlangaFollow