ML Project Ideas

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 2

Num Name Description Resources #Participants

1 Iris Classification The Iris Flowers data set is a very well-known and one Dataset: Download 3
of the oldest and simplest for machine learning
projects for beginners to learn. With this project,
learners have to figure out the basics of handling
numeric values and data. Data points include the size
of sepals and petals by length and width. Using
machine learning, a successful project classified irises
into one of three species.
2 Ukraine & Russia The mentioned dataset contains daily updates about Dataset: Download 3
conflict the Russia& Ukraine conflict losses on both sides, do
the required data pre-processing, then select an
appropriate machine learning algorithm to make
predictions about the losses of both sides for the next
7
3 Heart Disease dataset gives some key indicators of a heart disease Dataset: Download 3
indicator make the required preprocessing, select machine
learning algorithm to classify whether this patient has
a heart disease or not.
4 Story This project is built on a Jupyter notebook using Choose any large 3
summarization Python with Numpy, sklearn and genism to train text story
large-scale semantic NLP models. Story
summarization is the process of creating a short,
accurate, and fluent summary of a long story. It is the
process of distilling the most important information
for a text document.
5 Housing Prices The dataset has the house prices. Dataset: Download 3
Prediction The expense of the house varies according to various
factors like view, rooms, condition, etc.
6 Head pose Head pose estimation is application that heavily relies Dataset: Download 4
estimation on face detection. Estimating the head pose is useful
in the settings of automated guided cars, where an in-
car device runs the head pose estimation algorithm to
detect the drowsiness of the driver.
This project is built on a Jupyter notebook using
Python with Numpy and scikit-learn to find and
identify human faces in digital images. Many methods
have been proposed in the field of the face detection.
the methods based on a skin color can detect any
sizes and poses of the face.
7 Breast Cancer predict if a cancer cell is good or bad (or in medical Dataset: Download 5
prediction terms: malignant or benign). Here we have 30
different features for each cancer cell that have been
computed from medical images.
8 Music use the dataset from Asia's leading music streaming Dataset: Download 4
Recommendation service to build a better music recommendation
system. We will try to determine which new song or
which new artist a listener might like based on their
previous choices. The primary task is to predict the
chances of a user listening to a song repetitively
within a time frame. In the dataset, the prediction is
marked as 1 if the user has listened to the same song
within a month. The dataset consists of which song
has been heard by which user and at what time.
9 Fake News Due to the sheer volume and speed of data across the Dataset: Download 4
Classification internet, it is not possible to take every news clip and
have it analyzed by an expert. Hence, a technique to
determine fake news by applying methods based on
Natural Language Processing are proposed to identify
fake news in real-time and prevent the spread of
misinformation
10 Spam filter this project is interesting because it is implemented in Dataset: Download 4
everyones email client. Here we want to create a
spam filter based on the Spam base dataset. In this
dataset we have the frequency of different words and
characters, so we calculate the total number of
appearances of each word and divide it by the total
number of words in the email. Spam emails clearly
show certain key words more often than normal
mails, so with this information we are able to create a
spam classifier. As algorithm I recommend having a
look at the Naive Bayes algorithm here. The new
challenge here is then not only to use this dataset and
evaluate your model, but then after you have trained
your classifier also apply it to a real application. So,
what do you do with a new email? What do you have
to do before you pass it to the classifier? Here you
somehow have to find out how to transform the text
from the email to the same format that your classifier
expects. This should give you a better understanding
of how datasets are shaped and created.

You might also like