All companies look for talented and smart employees though your age, qualification, cgpa/percentage might just matter to some extent. Your experience and how well you are versed in the field matters the most. Learning ML algorithms is good. But the projects you work on are very important. They say a lot about your practical knowledge in the field. Choose projects from different levels, from beginner to advanced, and from regression to deep learning. Create projects on different streams like core science, medical, stocks, business analysis, banking, speech recognition, etc. This way you can also find the stream you are more comfortable with and challenges you to code well. This gives you a lot of knowledge. ML is a vast subject, dive into it.
It is important to make an impression. As they say “The first impression is the best impression”. So, you need to have some good projects on your resume to make that good impression, don’t you think?
Here are some projects that work like magic on your resume:
Chatbots are artificial intelligence software that stimulates conversations with the user in natural language across various social interaction channels such as messaging applications, websites, customer care services, or mobile applications. No wonder they are so popular.
Steps to create a chatbot:
1. Import libraries and load the dataset.
2. Preprocessing data. (Crucial)
3.Split the dataset for training and testing
4.Build a model and predict.
Image Courtesy of pbs.twimg.com
Yes, it does make an impression of having a big tech team. But really all you need is a good dataset, modeling, and a hint of your creativity to make it an efficient one.
Tip:try making a chatbot in regional languages or languages other than English.
Facial recognition is a technology that is capable of recognizing a person based on their face. It employs machine learning algorithms that find, capture, store, and analyze facial features to match them with images of individuals in a pre-existing database.
This is a very interesting one. We use this feature to unlock our phones. Face filters also need this to work. Google photos also use this feature to categorize photos into albums based on people. Now you can also make one using ML algorithms.
There are a lot of different types of models you can make using this like emotion detection, ethnicity detection, person identification, cartoonize faces, and a lot more.
Few crucial steps for creating the project:
1.Image preprocessing.
2.Feature Extraction and classification.
This is not going to be an easy one but you will get there (You have to :/)
This is similar to face recognition but you can do it for objects. This can be used to identify objects in images or videos. This also needs a lot of processing. It a very challenging one too.
Steps to create the project:
1. Import libraries and datasets
2.Extract features
3.Create a dictionary for different emotions.
4.Split the dataset into train and test sets.
5.Get features and use a multi-layer perception (MLP) classifier to train the model.
Sentiment Analysis is contextual mining of text which identifies and extracts subjective information in the source material and helping a business to understand the social sentiment of their brand. It helps the brands to know,
What are the product aspects that customers like/dislike the most?
Reactions of the customers to the products.
A rather easy one I would say but interesting. You will have fun making it. You can collect data from amazon reviews, IMDB reviews, Twitter datasets (a pretty popular one), and many more. There are hundreds of datasets available online for this. But it tests your NLP knowledge and skills. Choose a good dataset and classifier. For this one, the larger the dataset, the better the model. For this project, along with the sentiment analysis of the review or the sample it is also important to know the underlying intention of the customer behind that, this gives us a more accurate model.
Steps to create the project:
1.Import necessary libraries and datasets.
2.Data preprocessing includes removing regular expressions, stemming, tokenization, etc.
3.Feature extraction (You can use the most common words in the bag of words as features).
4.Split the dataset.
5.Build a model and train.
6.Predict for the test dataset.
Looks like someone’s in great need of Sentiment Analysis. Make sheldon happy, y’all 😉
Jokes apart. This is a serious issue! There is a lot of fake news spreading around may it be Facebook, random websites, or those WhatsApp forward messages. Especially in this internet era, it is very difficult to control identify which is fake news and which is not. During covid times, fake news is dangerous too. With this project, you can address this problem. Make your model accurate but DO NOT overfit. On this note, do not spread false news around.
Steps involved:
1.Import necessary libraries and datasets.
2.Data preprocessing includes removing regular expressions, stemming, tokenization, labeling, etc.
3.Feature extraction.
4.Split the dataset.
5.Build a model and train.
6.Predict for the test dataset.
I hope you didn’t fall for this meme ;p
Few more ideas to make your resume look impressive:
Covid-19 Analysis.
To read handwriting.
Write ML algorithms from scratch.
About the author:
Smruthi R Paladhi, pursuing 3rd year engineering in Bangalore.
Follow me on Instagram: @photo.craftt
The media shown in this article are not owned by Analytics Vidhya and are used at the Author’s discretion.
We use cookies on Analytics Vidhya websites to deliver our services, analyze web traffic, and improve your experience on the site. By using Analytics Vidhya, you agree to our Privacy Policy and Terms of Use.Accept
Privacy & Cookies Policy
Privacy Overview
This website uses cookies to improve your experience while you navigate through the website. Out of these, the cookies that are categorized as necessary are stored on your browser as they are essential for the working of basic functionalities of the website. We also use third-party cookies that help us analyze and understand how you use this website. These cookies will be stored in your browser only with your consent. You also have the option to opt-out of these cookies. But opting out of some of these cookies may affect your browsing experience.
Necessary cookies are absolutely essential for the website to function properly. This category only includes cookies that ensures basic functionalities and security features of the website. These cookies do not store any personal information.
Any cookies that may not be particularly necessary for the website to function and is used specifically to collect user personal data via analytics, ads, other embedded contents are termed as non-necessary cookies. It is mandatory to procure user consent prior to running these cookies on your website.
A very informative article! All the best :)