Types of decision support systems and how a decision engine compares
The essentials in 30 seconds
- Types of decision support systems fall into 5 groups: communication, data, document, knowledge and model driven.
- Each type hands the person a different kind of material.
- A decision engine fixes its dimensions in advance and weighs the factors itself.
- The EQOS Asia engine uses 9 dimensions and flags a STOP zone below 0.618 (EQOS Asia method page, as of October 2026).
- A three-point check helps match a type to a question.
Types of decision support systems are usually grouped by the way they assist the user: through conversation, data, documents, rules or models. This guide describes the 5 types in plain terms and compares a decision engine with each of them. The comparison extends the parent guide on how the two relate, and it keeps the focus on what each type contributes to a choice.
On this page
Compare the EQOS Asia offers and request a 30-minute pre-diagnostic.
How are types of decision support systems classified?
The most cited classification sorts systems by their dominant mode of assistance. Wikipedia lists 5 types: communication-driven, data-driven, document-driven, knowledge-driven and model-driven (Wikipedia, Decision support system, consulted October 2026). The grouping answers one question about each tool: what does it hand to the person making the decision? A conversation space, a body of data, a set of files, a rulebook or a calculation each answer differently.
A classification by assistance helps because organisations rarely buy only one type. A finance team may run a data-driven reporting layer, a model-driven planning tool and a shared workspace for committee papers. Seeing the types side by side shows which kind of help is already covered and which kind is missing. The missing kind is often the weighing of many factors into one comparable result.
What do communication-driven types of decision support systems offer?
Communication-driven types support teamwork, letting several people work on one task together (Wikipedia, Decision support system, consulted October 2026). Their value grows with the number of participants and the number of locations. A committee spread across Singapore, Hong Kong and Tokyo can annotate the same paper and read each other’s comments. The type shapes how a discussion runs.
What it contributes is shared context and a record. What it leaves to the group is the content of the judgement. A shared workspace hosts the conversation in which people argue which option ranks first. For decisions that need a repeatable comparison, groups pair this type with one of the calculating types described below.
How do data-driven and document-driven decision support systems differ?
A data-driven type centres on access to a time series of internal company data, sometimes enriched with external data (Wikipedia, Decision support system, consulted October 2026). It suits questions that start with a number, such as revenue by channel or delay by supplier. Analysts query it, managers read the charts, and the output describes the past or the present state of the business.
A document-driven type handles unstructured information in many electronic formats, including storing, retrieving and editing it. It suits questions that start with a text, such as which clauses appear in supplier contracts. Data-driven types return figures, and document-driven types return passages. Both prepare the evidence, and a reader forms the conclusion.
What sets knowledge-driven decision support systems apart?
A knowledge-driven type supplies problem-solving expertise stored as rules, facts or procedures, often shown as decision trees and flowcharts (Wikipedia, Decision support system, consulted October 2026). A compliance checklist that routes an application to the right approver is a simple instance. The expertise of a senior colleague becomes available to everyone, and answers stay consistent from one case to the next.
Its boundary is the number of conditions a person can maintain. Every new factor adds branches, and every branch needs an owner. Teams that reach this boundary often look for a way to score many factors together, a step that a decision engine covers with weighted dimensions in place of a growing tree.
What does a model-driven decision support system calculate?
A model-driven type works with statistical, financial, optimisation or simulation models, using parameters that the user supplies, and it can run on modest data (Wikipedia, Decision support system, consulted October 2026). A capacity planner who tests 3 demand curves in a simulation is a typical user. The model turns assumptions into outputs, and the user varies the assumptions to explore.
This type sits closest to a decision engine, because both calculate. The difference lies in what is fixed. A planning model follows the structure its author chose for one problem. A decision engine fixes the dimensions and the aggregation in advance, so different decisions are measured on the same yardstick and results can be compared across cases.
How does a decision engine compare with these types of decision support systems?
Set the 5 types against a decision engine on 3 points: what the system holds, who weighs the factors, and what comes out. The first 4 types, communication, data, document and knowledge, hold conversation, figures, files or rules, and a person weighs the factors. A decision engine holds a fixed structure of dimensions and weighs the factors itself. The figure lines the points up.
The EQOS Asia engine illustrates the last row. It scores a situation on 9 dimensions, returns a φ(S) value between 0 and 1, and marks a STOP zone below 0.618 (EQOS Asia method page, as of October 2026). Because the core is deterministic, a second run with the same inputs returns the same value, which supports review by a committee or an auditor.
How do you choose among the types of decision support systems?
Start from the question. A question about what happened points to a data-driven type, a question about a text points to a document-driven type, and a question about a routine case points to a knowledge-driven type. A question about what happens under different assumptions points to a model-driven type. A question about how several dimensions combine points to a decision engine.
Then test the choice with 3 checks. Can a second person reproduce the output? Can an executive read it in 5 minutes? Does it show which factor drives the result? The simulator offers a first look at such a result, the method page explains the 9 dimensions, and the pricing page lists a Reading at US$358 (EQOS Asia pricing page, as of October 2026). This page is general information, not legal, tax or investment advice.
See also in this guide
Frequently asked questions
How many types of decision support systems exist?
A widely cited classification lists 5 types: communication-driven, data-driven, document-driven, knowledge-driven and model-driven (Wikipedia, Decision support system, consulted October 2026). Each type is defined by the kind of help it gives the person who decides.
Which type of decision support system is closest to a decision engine?
The model-driven type, because both calculate. A model follows the structure its author chose for one problem, while a decision engine fixes its dimensions and aggregation in advance so that many decisions share one yardstick and can be compared.
Does a decision engine replace the other types?
A decision engine adds a scoring step and leaves the other types in place. Dashboards still show facts, documents still carry evidence, and workspaces still host discussion. The engine weighs the factors and returns a result that the team can then debate with a shared reference.
What does the EQOS Asia engine output?
It outputs a φ(S) score between 0 and 1 computed on 9 structural dimensions, with a STOP zone below 0.618 and a list of 3 priority risks (EQOS Asia method page, as of October 2026). The core is deterministic, so a reviewer can recompute any verdict.
Test your knowledge
1. How many types appear in the classification used on this page?
- 5
- 3
- 9
Show the answer
5.
2. Which type stores expertise as rules and decision trees?
- Data-driven
- Knowledge-driven
- Communication-driven
Show the answer
Knowledge-driven.
3. Which type sits closest to a decision engine?
- Document-driven
- Communication-driven
- Model-driven
Show the answer
Model-driven.
4. Below which φ(S) value does the STOP zone begin?
- 0.618
- 0.100
- 0.900
Show the answer
0.618.
5. Who weighs the factors in a decision engine?
- A committee vote
- The engine itself
- A shared document
Show the answer
The engine itself.
About the author
Stéphane Jambu
President, EQOS Forecast Asia
Stéphane Jambu leads EQOS Forecast Asia and works as a consultant in e-commerce, search visibility, and AI. LinkedIn profile
Sources: EQOS Asia method page (eqos-asia.com/method.html), simulator page (eqos-asia.com/simulator.html) and pricing page (eqos-asia.com/pricing.html), en.wikipedia.org/wiki/Decision_support_system, consulted on 22 October 2026. Page updated on 22 October 2026.