AI PROJECT CYCLE - ACTIVITY 2

Objective of the assessment:

To evaluate students' understanding of the basics of the AI project cycle by requiring them to propose a
hypothetical AI project..

From the below, choose a theme for your project and provide a title for your AI project. Clearly articulate the
main objective or problem that the AI system aims to address.

*You may also choose a theme that is aligned to any one of the 17 SDGs.

Selected theme: ……………………

Reason for selecting this theme:

A theme is a broad term that covers all the aspects of relevance under it. For example, In Agriculture, there
are pest issues, yield rates, sowing and harvesting patterns, etc. all being very different from each other but
still a part of the Agriculture theme. Thus, to effectively understand the problem and elaborate it, we need to
select one topic under the theme.

Therefore, under the theme you have selected, list various topics of relevance:
Of the various topics listed, choose any one topic for which you would like to develop an AI solution for:

Topic chosen: ………………………………………………………………….

Now list down the problems which come under our Topic. You can recall daily life scenarios where you may
have witnessed problems related to the Topic of your choice. You may conduct an online research around
your chosen topic.

Under the chosen theme The list of problems encountered are:

…………………………………………………….. 1.
2.
and selected topic of 3.
4.
……………………………………………………… 5.

Select one problem out of the ones listed above which you want to solve using your AI knowledge. This
Problem now becomes the target of your AI project and helps you get a clear vision of what is to be
achieved.

Now frame the selected problem as a goal. For example, a goal can be stated as How might we help farmers
determine the best times for seeding and for sowing their crops?

Write the goal of your project here:

Use the 4W canvas problem canvas to help you identify the key elements related to the problem.
Complete the 4W canvas for your problem statement:

WHO? WHAT?

WHERE? WHY?

Now summarise all the cards into one template. The Problem Statement Template helps us to summarize all
the key points into one single Template so that in future, whenever there is need to look back at the basis of
the problem, we can take a look at the Problem Statement Template and understand the key elements of it.

Our _______________________[Stakeholders]_________________________ has/have a problem that

_________________________[issue, problem, need]____________________ when/while
_____________________________________[context, situation].

An ideal situation would be________________________[benefit of solution for them]____________.

Now that you have completed the Problem scoping phase of your project cycle, work towards the Data
acquisition phase.

Look at your problem statement once again and try to find the data features required to address this issue.
Data features refer to the type of data you want to collect.

For example, If you want to make an Artificially Intelligent system which can predict the salary of any
employee based on his previous salaries, you would feed the data of his previous salaries into the machine.
This is the data with which the machine can be trained. Now, once it is ready, it will predict his next salary
efficiently. The previous salary data here is known as Training Data while the next salary prediction data set is
known as the Testing Data.
Data features for this example would be: salary amount, increment percentage, increment period, bonus, etc.
Now try to find out what are the parameters which affect your problem statement directly or indirectly and list
them down below.

Problem statement:

Data features: (list at least 5)

List down ways for acquiring data for your project:

Some of the open-sourced Govt. portals are: data.gov.in, india.gov.in

Now that you have completed the Data acquisition phase of your AI project cycle, you must have noticed
that the data is a complex entity – it is full of numbers and if anyone wants to make some sense out of it, they
have to work some patterns out of it.

For example, if you go to the library and pick up a random book, you first try to go through its content quickly
by turning pages and by reading the description before borrowing it for yourself, because it helps you in
understanding if the book is appropriate to your needs and interests or not.

Thus, to analyse the data, you need to visualise it in some user-friendly format so that you can:
● Quickly get a sense of the trends, relationships and patterns contained within the data.
● Define strategy for which model to use at a later stage.
● Communicate the same to others effectively.

To visualise data, we can use various types of visual representations.

To explore various data visualisation techniques, visit this link: https://datavizcatalogue.com/
In order to visualise your data, select one of the representations from the link or choose the ones which you
already know. The basis of your selection should be the data feature which you want you to visualise in that
particular representation. Do this for all the data features you have for the problem you have scoped.

For example, if the problem statement is: How can we predict whether a song will make it to the billboard's
top 10? We would require data features like Current trends of music, the genre of music, the tempo of the
music, duration of the song, the popularity of a singer, etc.
Now to analyse a pattern, we can say that the popularity of the singer would directly have an effect on the
output of the system. Thus, we would plot a graph showing the popularity of various singers and the one who
is most popular has the maximum chance of getting to the billboard.

In this way, the graphical representation helps us understand the trends and patterns out of the data
collected and to design a strategy around them for achieving the goal of the project.

For your AI solution:

1. What data feature are you going to represent?

2. Which representation are you going to use for this data feature? Why?

3. Represent your data features in various types of graphs (at least 3)

4. List down the trends you may have observed in your representations:
Now that the data exploration is complete, Choose an appropriate model to build your AI solution.

For example, If the goal was to develop an AI-powered system to optimise waste management processes in
urban areas, aiming to reduce environmental impact and promote sustainability.
● Models: Implement machine learning models for predicting optimal waste collection schedules based
on historical data and current trends.
● Rationale: Machine learning allows for dynamic scheduling, adapting to changing waste generation
patterns and optimising collection routes.
● Considerations: Consider the environmental impact of transportation and balance between over- and
under-collection.

1. Specify the type of AI models you plan to use for your project.

2. Provide a rationale for choosing these models based on the nature of the problem.

3. Discuss any considerations related to model selection and parameters.

To complete your AI project cycle, an Evaluation of the AI solution must be conducted.

For the above example, the evaluation may be completed as below,

● Feedback Loop: Collect user feedback on recommended items to improve the model.
● Iterative Process: Refine the model based on ongoing evaluation, adapting to changing user
preferences.
● Challenges: Balancing precision and recall, minimising false positives, and addressing evolving user
behaviour.

1. Explain how you will assess the performance of your AI model.

2. Discuss the iterative nature of the evaluation phase and how it informs model refinement.
 3. What are some of the challenges that you foresee in the evaluation of your AI solution’s
efficiency?

Complete the final reflections for this Activity:

1. Summarise key points from each phase of the AI project cycle.

2. Outline what may be the next steps after the completion of the AI project cycle.

3. Reflect on the potential impact of the proposed AI solution.