liveBook · Manning

Hybrid approach

As explained in Fight Fraud with Machine Learning

A hybrid system combines multiple decision mechanisms, such as rules, machine learning, and deep learning.

A hybrid approach combines rules, machine learning, and deep learning when fraud data mixes structured and unstructured elements. It suits semi-structured settings where tabular signals and text or images must inform detection together. section 1.5

Phishing detection

A phishing detector can combine structured signals such as IP address and receipt time with unstructured email body and header text. Rules may handle limited structured data, while machine learning or deep learning extends detection as data availability grows. section 1.5

Figure 1.16 Example of different data modalities hypothetically used (?) for a phishing fraud example. The Structured dataset contains only tabular data with decimal and binary numbers, the unstructured dataset contains natural text and images, and the semi-structured dataset contains elements of both the structured and unstructured dataset.

Compare tabular structured data, natural text and images, and mixed semi-structured data in a phishing-fraud setting. section 1.5

How Fight Fraud with Machine Learning covers it

How deep it goes
Defines modality-based model selection and combination but stops short of implementation, training, or deployment procedures.
Examples
Uses phishing detection with IP addresses, receipt times, email bodies, and header text as mixed inputs.
What you can do after
Evaluate which combination of rules, machine learning, and deep learning fits the available fraud data modalities.
How it connects
Connects structured data, unstructured data, semi-structured data, rules-based systems, machine learning, and deep learning.

Also explained in

Compare how 8 books explain hybrid approach →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Fight Fraud with Machine Learning. The section links point to the parts of the book it draws on.