liveBook · Manning

Problem definition

Also called problem statement, problem formulation

A problem definition is a specification of a problem’s goals, context, and relevant constraints that guides its analysis or solution.

How 8 Manning books explain it

AI for Everyday IT

Problem formulation is the process of defining and structuring a problem precisely so that it can be analyzed and solved effectively.

How it is used
Guides AI requests by defining the desired outcome and solution structure before prompt engineering.
How deep it goes
Explains problem breakdown and expert guidance, then demonstrates how to add context and requirements to prompts.
Examples
Contrasts Python sorting prompts and uses a spreadsheet-driven project documentation template.
What you can do after
Apply it to structure AI requests around specific goals, requirements, and deliverables.

Read how AI for Everyday IT explains problem definition →

Get Programming: Learn to code with Python

A description of the task a program is expected to accomplish, including relevant inputs, interactions, and outputs.

How it is used
Frames the task before coding by identifying what the program must accomplish and how it should behave.
How deep it goes
Gives a planning checklist and walks through sketches, sample cases, and pseudocode; leaves implementation steps to be worked out.
Examples
Uses bread requests of varying specificity and a two-name mashup with varied test inputs.
What you can do after
Practice/perform it by sketching inputs and outputs, choosing test cases, and dividing a task before coding.

Read how Get Programming: Learn to code with Python explains problem definition →

Starting Data Analytics with Generative AI and Python

A precise formulation of the real problem that an analysis is intended to address.

How it is used
Frames an initial business question before analysis begins, connecting it to the decision the analysis should support.
How deep it goes
Moves from surface symptoms to underlying business problems and scope, while deferring the later analytical workflow.
Examples
Uses patient waiting times on Tuesdays and customer loyalty-card use as initial questions requiring deeper interpretation.
What you can do after
Apply it via guided questions to convert a received request into a more valuable, decision-enabling analytical starting point.

Read how Starting Data Analytics with Generative AI and Python explains problem definition →

Machine Learning System Design

A concise written description of a problem, including its relevant goals, context, and important characteristics.

How it is used
Frames the organizational problem before beginning ML system design or selecting technical approaches.
How deep it goes
Builds a top-down questioning process from helicopter-level statements to problem nuances and valuable data.
Examples
Uses fraud attacks, weak margins, manual tuning, and low user engagement as workplace problem statements.
What you can do after
Evaluate/understand an ML initiative's broad goal and identify the information needed before implementation begins.

Read how Machine Learning System Design explains problem definition →

Build Financial Software with Generative AI (From Scratch)

Problem formulation is the practice of specifying a problem's context, objective, constraints, and observable failure precisely.

How it is used
Uses precise problem definition to guide generative-AI requests and obtain code aligned with developer intent.
How deep it goes
Defines clarity, concision, correctness, and examples for prompts, but does not develop a formal requirements method.
Examples
Uses progressively refined Python balance-formatting examples, moving from direct printing to a typed function that returns a string.
What you can do after
Apply it via prompt engineering to request clearer, more reusable generated code.

Read how Build Financial Software with Generative AI (From Scratch) explains problem definition →

Build AI Drug Discovery Pipelines

Problem definition is the specification of a predictive or analytical task, its success criteria, and whether a chosen method is appropriate.

How it is used
Frames cardiotoxicity screening as a decision problem before selecting data, features, models, and evaluation criteria.
How deep it goes
Defines requirements, labels, failure costs, and uncertainty, then stops short of production deployment and maintenance.
Examples
Uses Malaria Box similarity hits, hERG blocker labels, experimental follow-up, and two contrasting screening failure cases.
What you can do after
Evaluate/understand whether a machine-learning screening task has defined labels, risks, constraints, and useful success criteria.

Read how Build AI Drug Discovery Pipelines explains problem definition →

Machine Learning Platform Engineering

Problem formulation is the process of translating a real-world objective into a precisely defined machine learning problem with suitable inputs, outputs, and success criteria.

How it is used
Frames the business objective, technical feasibility, data needs, and governance constraints before model development begins.
How deep it goes
Provides a stakeholder question set and lifecycle placement, but stops short of specifying implementation algorithms or code.
Examples
Contrasts vague customer-churn prediction with vehicle-price prediction and uses stakeholder questions as a practical checklist.
What you can do after
Apply it by aligning stakeholders on the task, success metrics, data, risks, deployment approach, and retraining signals.

Read how Machine Learning Platform Engineering explains problem definition →

Timeless Algorithms, The Foundational Ideas

Problem formulation is the process of specifying a problem's states, decisions, constraints, objectives, and relationships in a form suitable for analysis or computation.

How it is used
Frames multi-stage optimization problems so dynamic programming can relate stage decisions to an overall solution.
How deep it goes
Specifies states, transitions, recurrences, and base cases, leaving execution as the next task.
Examples
Uses knapsack and coin change to illustrate a shared framework across optimization problems.
What you can do after
Build a dynamic-programming formulation by specifying states, transitions, recurrence relations, and base cases.

Read how Timeless Algorithms, The Foundational Ideas explains problem definition →

Also covered in

What to know first

Related concepts

Questions about problem definition

What is problem definition?

A problem definition is a specification of a problem’s goals, context, and relevant constraints that guides its analysis or solution.

Which Manning books explain problem definition?

AI for Everyday IT, Get Programming: Learn to code with Python, Starting Data Analytics with Generative AI and Python, Machine Learning System Design, Build Financial Software with Generative AI (From Scratch), Build AI Drug Discovery Pipelines, Machine Learning Platform Engineering and Timeless Algorithms, The Foundational Ideas.

What should I know before learning problem definition?

Manning books that teach problem definition usually introduce language model, conversational ai, input and metaheuristic first.

What is the difference between problem definition and prompt engineering?

A problem definition is a specification of a problem’s goals, context, and relevant constraints that guides its analysis or solution. Prompt engineering is the deliberate design and refinement of inputs, instructions, and context to guide an AI model’s behavior or outputs.

What is problem definition part of?

Problem definition is part of machine learning workflow. A machine learning workflow is an organized sequence of activities for formulating, developing, evaluating, deploying, operating, and maintaining a machine learning system.

What are the parts of problem definition?

Problem definition includes decision variable, constraint and objective function.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.