Unit 21: Introduction to Artificial Intelligence (AI) Assignment Brief
| Qualification | Pearson BTEC International Level 3 Qualifications in Information Technology |
| Unit number and title | Unit 21: Introduction to Artificial Intelligence (AI) |
| Learning aim(s) (For NQF only) | A: Investigate uses and applications of AI
B: Plan and prepare an AI solution to meet identified needs C: Develop an AI solution to meet identified needs. |
| Assignment title | Investigate, explore, and train your first model. |
Vocational Scenario or Context
You are an independent Junior Developer. To build your portfolio, you have decided to identify a real-world problem in a field you are passionate about (e.g., sports, music, gaming, or local business) and solve it using AI. You must work on an individual project, meaning your data, goals, and AI model must be unique to your chosen topic. You will document the whole process from researching AI concepts to building a working model.
Task 1
Task 1: AI Investigation (Learning Aim A)
Objective: Explain how AI works and how it specifically relates to your chosen individual project.
- A1: Define AI and explain its fundamental concepts. Is your chosen project an example of “Weak AI” or “Strong AI”?
- A1: Identify which type of AI (e.g., Limited Memory) and which subset (e.g., Machine Learning, NLP, Computer Vision) you will utilize in your project.
- A2: Document the ethical and legal implications of your project (e.g., data privacy and GDPR compliance).
- A2: Outline the AI development process (AI Pipeline) you will follow for your specific solution.
Task 2: Data for My Project (Learning Aim B)
Objective: Plan, gather, and prepare the necessary “fuel” (data) for your AI solution.
- B1: Identify and justify your data sources (e.g., Kaggle, social media APIs, or manual collection).
- B1: Analyze your data formats (e.g., CSV, JSON) and evaluate them against the “Five Vs” of Big Data (Volume, Velocity, Variety, Veracity, Value).
- B2: Perform data cleansing activities (removing redundancy, fixing errors, handling missing values) and provide screenshots as evidence of this process.
Task 3: Building the AI Solution (Learning Aim C)
Objective: Develop the code for the AI model and evaluate the results.
- C1: Select an appropriate AI model based on your problem type (e.g., Regression for numerical predictions, Classification for categories, or Clustering for grouping).
- C2: Write the code for your model using Python and relevant libraries (e.g., Scikit-learn, TensorFlow, or Pandas).
- C2: Test and validate your model (e.g., using an 80/20 split for training and testing). Report on the model’s accuracy and performance.
Checklist of Evidence Required
(A) Completed report
(B) A written report on the results of the analysis
(C) Evidence of data preparation and cleaning (screenshot). Report for the head of the business.
Criteria covered by this task:
| Unit/Criteria reference | To achieve the criteria, you must show that you are able to: |
| A.D1 | Evaluate the impact of AI on different industries. |
| A.M1 | Analyse the benefits, risks and drawbacks of AI and how they impact on different industries. |
| A.P1 | Describe how the fundamental concepts of AI are used in industry to meet specific identified needs. |
| A.P2 | Explain the associated benefits, risks and drawbacks of AI in different industries. |
| B.D2 | Evaluate the effectiveness of the AI solution. |
| B.M2 | Review and refine data sets to optimise the quality of an AI solution. |
| B.P3 | Define the objectives of an AI project. |
| B.P4 | Gather and prepare appropriate data sets for an AI solution. |
| C.D3 | Evaluate the effectiveness of the AI solution. |
| C.M3 | Test and refine the AI solution. |
| C.P5 | Develop an AI solution using an appropriate programming language and computing tools. |
Sources of information to support you with this Assignment
Evans, J. (2016) Business Analytics. 2nd Ed. Pearson.
Cody, I.D. Data Analytics: Practical Data Analysis and Statistical Guide to Transform and Evolve Any Business Create Space Independent Publishing Platform. 2016 978-1536875379
Runkler T. (2016) Data Analytics: Models and Algorithms for Intelligent Data Analysis. 2nd Ed. Vieweg Teubner Verlag.
Are You Searching Answer of this Question? Request British Writers to Write a plagiarism Free Copy for You.
Chat Now