Planning a Machine Learning Project Flashcards

1
Q

How can businesses determine if machine learning is the right solution for their problem?

A

Businesses can determine if ML is the right solution if the problem is clear and quantifiable. ML can provide value in a model’s predictions when compared to specific business objectives and success criteria.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is an example of a business problem where machine learning would be appropriate?

A

Generating personalized recommendations is an example where ML is appropriate due to the need for complex logic, scalability, personalization, and responsiveness.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Why is complex logic a reason to use machine learning for personalized recommendations?

A

Developing personalized recommendations requires complex logic that ML can handle effectively.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

How does machine learning help with scalability in personalized recommendations?

A

ML can serve millions of requests for personalized recommendations every second, meeting high scalability demands.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Why is personalization a critical factor for using machine learning in recommendations?

A

Delivering personalized recommendations at scale and being responsive at the same time is difficult to achieve with classical programming techniques, making ML a better fit.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

How does machine learning ensure responsiveness in handling recommendations?

A

ML can deliver personalized recommendations within a few seconds even while handling millions of requests per second.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

When might a traditional algorithm be preferred over machine learning?

A

If the problem is not overly complex, a traditional algorithm might be more appropriate and less complicated than ML.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Why might a business avoid machine learning if it does not need to adapt to new data?

A

If data and conditions are stable and not changing, traditional approaches could be more suitable than ML.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Why is 100% accuracy a reason to avoid using machine learning?

A

ML predictions often provide less than 100% accuracy, which may not meet the business goals that require complete accuracy.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Why might a requirement for full interpretability be a reason to avoid machine learning?

A

If being able to explain the outcomes and the effect of changing parameters is a priority, traditional methods may be preferable because ML models can be complex and less transparent.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is an example of a business case where machine learning is appropriate?

A

A financial institution needing to determine which category of products and offerings is most interesting to a customer is a good example. The problem might be too complex for simple hand-coded rules and may depend on many factors and overlapping rules, making ML an appropriate solution.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

How should you identify a good problem to solve using machine learning?

A

To identify a good problem for ML, determine your business outcome or goal and ask questions about strategy, the use of ML to achieve the goal, and the aspects of the problem that make it suitable for ML.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What question should you ask about strategy in relation to machine learning?

A

What is the strategy to achieve this goal?

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What types of data are available today?

A

ML uses training data optimized for learning and generalization. Models can ingest several types of data, including:

Documents
Audio
Images
Video
Weather reports
Website interactions
Social media connections
Industrial monitoring

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is the first step in identifying a problem for a machine learning solution?

A

The first step is to identify a problem that is rich in data but hasn’t been solvable through traditional methods. This approach is emphasized by Jenny Freshwater, director of forecasting at Amazon.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Is my data ready for a machine learning solution?

A

Data readiness depends on the quality, quantity, diversity, and complexity of the data collected. After discovering and collecting all relevant data, it should be cleansed, validated, transformed, and stored.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Is my data available?

A

Data should exist for training and model development and should not require significant preparation before use.

18
Q

Is my data accessible?

A

Data should be in a reachable, on-demand state with access to store, retrieve, move, modify, or copy data from one place to another.

19
Q

Does my data respect my customers’ privacy?

A

Personally identifiable information, such as citizenship or health information, might be labeled private and protected by privacy laws.

20
Q

Does my machine learning project have adequate security?

A

Industry regulations, government laws, and compliance policies determine the importance of various data types and determine what and how data can be processed, stored, managed, or shared.

21
Q

Is my data high quality?

A

Data used in an ML project should be:

Relevant: Produce valuable results
Fresh: Timely so that training data is as close to the actual data as possible
Representative: Reflect data across all data sources
Unbiased: Ensure fair representation

22
Q

Is my data relevant for the type of machine learning project I intend to build?

A

Example: If you are developing a machine learning solution for a forecasting model, but you don’t have data directly related to that goal, the data will not help you power the model. For any potentially relevant data, keep it on the list and assess its suitability.

23
Q

What is an example business case for data readiness?

A

Consider a banking institution that wants to gather quantifiable insights about a segment of customers. Leadership must decide if they meet data readiness requirements to use ML as a solution.

24
Q

What question should I ask about data readiness?

A

Is it easily accessible?

25
Q

What question should I ask about data readiness?

A

Does it respect privacy?

26
Q

What question should I ask about data readiness?

A

Is it relevant?

27
Q

How long does it typically take to deploy a machine learning model into production?

A

Machine learning projects can take significant time from start to deployment. Expectations for deploying production models can range from weeks to even months.

28
Q

What does a machine learning lifecycle look like?

A

The machine learning lifecycle consists of nine stages, and the entire process typically takes weeks or even months to complete.

29
Q

Will my machine learning model change over time?

A

Yes, the model may need to change over time. To maintain accuracy, the data distribution on which predictions are made should match the distribution of the training data. Since data distributions can drift, deploying a model is an ongoing process that requires continuous monitoring and retraining to adapt to new data.

30
Q

What is a best-case timeline for a machine learning project?

A

Even in the best-case scenario, deploying production models can still take weeks or months. A common misconception is that most of the time is spent in the Modeling, Training, and Testing stages; however, the overall timeline includes additional phases that contribute to the total duration.

31
Q

Can you provide an example of a business case where timeline challenges are a concern?

A

For instance, a manufacturer needing to use machine learning to solve a quantifiable business problem might be concerned about potential delays in deployment.

32
Q

What question should I ask about strategy?

A

Have you ever had a similar task to your proposed machine learning solution?

33
Q

What question should I ask about strategy?

A

Have you explored your data and found any faults?

34
Q

What question should I ask about strategy?

A

Is the performance of the models meeting the business requirements?

35
Q

How do I take my machine learning solution into production?

A

While production deployment of an ML model is one of the final stages of the ML pipeline, it’s important to note that production code differs significantly from research code. Research code is primarily for exploration and model validation, often lacking formal quality, stability, or scaling requirements. In contrast, production code must meet fixed requirements, facilitate collaboration through version control, maintain a code deployment history, and adhere to code reliability standards.

36
Q

What is the likely computational cost of generating predictions with your model?

A

Understanding the computational cost associated with generating predictions is crucial. This includes storage, processing, and other related expenses. Planning for these costs in advance can help avoid obstacles during production deployment and ensure that the model meets business requirements efficiently.

37
Q

How quickly does your data change?

A

Assessing how frequently your data changes is important as it impacts the complexity of the model and the frequency of retraining required. Frequent changes in data may necessitate more regular updates to the model, which can affect the time allocated for training and development.

38
Q

How significant are the changes needed to deploy?

A

Consider the extent of changes required for deployment and how often these changes will be made. This will help in strategizing the update process and maximizing the impact of new model versions.

39
Q

Does the model’s performance meet the business need?

A

Evaluate whether the model’s performance aligns with your business needs. Business conditions may evolve over time due to new product lines, regulations, or market expansions, and the model might need adjustments accordingly.

40
Q

Why is it important to answer these questions early in the production process?

A

Answering these questions early helps to identify and address potential issues before launching your machine learning model, facilitating a smoother deployment and ensuring that the model meets both technical and business requirements.