Data scientists are one of the most hirable specialists today, but it’s not so easy to enter this profession without a “Projects” field in your resume. Furthermore, you need the experience to get the job, and you need the job to get the experience. Seems like a vicious circle, right? Also, the great advantage of data science projects is that each of them is a full-stack data science problem. Additionally, this means that you need to formulate the problem, design the solution, find the data, master the technology, build a machine learning model, evaluate the quality, and maybe wrap it into a simple UI. Hence, this is a more diverse approach than, for example, Kaggle competition or Coursera lessons.
Hence, in this blog, we will look at 10 projects to undertake in 2019 to learn data science and improve your understanding of different concepts.
1. Match Career Advice Questions with Professionals in the Field
Problem Statement: The U.S. has almost 500 students for every guidance counselor. Furthermore, youth lack the network to find their career role models, making CareerVillage.org the only option for millions of young people in America and around the globe with nowhere else to turn. Also, to date, 25,000 create profiles and opt-in to receive emails when a career question is a good fit for them. This is where your skills come in. Furthermore, to help students get the advice they need, the team at CareerVillage.org needs to be able to send the right questions to the right volunteers. The notifications for the volunteers seem to have the greatest impact on how many questions are answered.
Your objective: Develop a method to recommend relevant questions to the professionals who are most likely to answer them.
2. Histopathologic Cancer Detection
Problem Statement: In this competition, you must create an algorithm to identify metastatic cancer in small image patches taken from larger digital pathology scans. Also, the data for this competition is a slightly different version of the PatchCamelyon (PCam) benchmark dataset. PCam is highly interesting for both its size, simplicity to get started on, and approachability.
Your objective: Identify metastatic tissue in histopathologic scans of lymph node sections
3. Aerial Cactus Identification
Problem Statement: To assess the impact of climate change on Earth’s flora and fauna, it is vital to quantify how human activities such as logging, mining, and agriculture are impacting our protected natural areas. Furthermore, researchers in Mexico have created the VIGIA project, which aims to build a system for autonomous surveillance of protected areas. Moreover, the first step in such an effort is the ability to recognize the vegetation inside the protected areas. In this competition, you are tasked with the creation of an algorithm that can identify a specific type of cactus in aerial imagery.
Your objective: Determine whether an image contains a columnar cactus
4. TMDB Box Office Prediction
Problem Statement: In a world, where movies made an estimate of $41.7 billion in 2018, the film industry is more popular than ever. But what movies make the most money at the box office? How much does a director matter? Or the budget? For some movies, it’s “You had me at ‘Hello. In this competition, you’re presented with metadata on over 7,000 past films from The Movie Database to try and predict their overall worldwide box office revenue. Also, the data points provided include cast, crew, plot keywords, budget, posters, release dates, languages, production companies, and countries. Furthermore, you can collect other publicly available data to use in your model predictions.
Your objective: Can you predict a movie’s worldwide box office revenue?
5. Quora Insincere Questions Classification
Problem Statement: An existential problem for any major website today is how to handle toxic and divisive content. Furthermore, Quora wants to tackle this problem head-on to keep their platform a place where users can feel safe sharing their knowledge with the world. On Quora, people can ask questions and connect with others who contribute unique insights and quality answers. A key challenge is to weed out insincere questions — those founded upon false premises, or that intend to make a statement rather than look for helpful answers.
In this competition, you need to develop models that identify and flag insincere questions. Moreover, to date, Quora has employed both machine learning and manual review to address this problem. With your help, they can develop more scalable methods to detect toxic and misleading content.
Your objective: Detect toxic content to improve online conversations
6. Store Item Demand Forecasting Challenge
Problem Statement: This competition is provided as a way to explore different time series techniques on a relatively simple and clean dataset. You are given 5 years of store-item sales data and asked to predict 3 months of sales for 50 different items at 10 different stores. What’s the best way to deal with seasonality? Should stores be modelled separately, or can you pool them together? Does deep learning work better than ARIMA? Can either beat xgboost? Also, this is a great competition to explore different models and improve your skills in forecasting.
Your Objective: Predict 3 months of item sales at different stores
7. Web Traffic Time Series Forecasting
Problem Statement: This competition focuses on the problem of forecasting the future values of multiple time series, as it has always been one of the most challenging problems in the field. More specifically, we aim the competition at testing state-of-the-art methods designed by the participants, on the problem of forecasting future web traffic for approximately 145,000 Wikipedia articles. Also, the sequential or temporal observations emerge in many key real-world problems, ranging from biological data, financial markets, weather forecasting, to audio and video processing. Moreover, the field of time series encapsulates many different problems, ranging from analysis and inference to classification and forecast. What can you do to help predict future views?
Problem Statement: Forecast future traffic to Wikipedia pages
8. Transfer Learning on Stack Exchange Tags
Problem Statement: What does physics have in common with biology, cooking, cryptography, diy, robotics, and travel? If you answer “all pursuits are under the immutable laws of physics” we’ll begrudgingly give you partial credit. Also, If you answer “people chose randomly for a transfer learning competition”, congratulations, we accept your answer and mark the question as solved.
In this competition, we provide the titles, text, and tags of Stack Exchange questions from six different sites. We then ask for tag predictions on unseen physics questions. Solving this problem via a standard machine approach might involve training an algorithm on a corpus of related text. Here, you are challenged to train on material from outside the field. Can an algorithm learn appropriate physics tags from “extreme-tourism Antarctica”? Let’s find out.
Your objective: Predict tags from models trained on unrelated topics
9. Digit Recognizer
Problem Statement: MNIST (“Modified National Institute of Standards and Technology”) is the de facto “hello world” dataset of computer vision. Since its release in 1999, this classic dataset of handwritten images has served as the basis for benchmarking classification algorithms. As new machine learning techniques emerge, MNIST remains a reliable resource for researchers and learners alike. Furthermore, in this competition, your goal is to correctly identify digits from a dataset of tens of thousands of handwritten images.
Your objective: Learn computer vision fundamentals with the famous MNIST data
10. Titanic: Machine Learning from Disaster
Problem Statement: The sinking of the RMS Titanic is one of the most infamous shipwrecks in history. On April 15, 1912, during her maiden voyage, the Titanic sank after colliding with an iceberg, killing 1502 out of 2224 passengers and crew. Furthermore, this sensational tragedy shocked the international community and led to better safety regulations for ships. Also, one of the reasons that the shipwreck led to such loss of life was that there were not enough lifeboats for the passengers and crew. Although there was some element of luck involved in surviving the sinking, some groups of people were more likely to survive than others, such as women, children, and the upper-class. In this challenge, we ask you to complete the analysis of what sorts of people were likely to survive.
Your objective: Predict survival on the Titanic and get familiar with ML basics
The best way to showcase your Data Science skills is with these 5 types of projects:
- Deep Learning
- Natural Language Processing
- Big Data
- Machine Learning
- Image Processing
Hence, be sure to document all of these on your portfolio website.
Follow this link, if you are looking to learn more about data science online!
You can follow this link for our Big Data course!
Additionally, if you are having an interest in learning Data Science, click here to start
Furthermore, if you want to read more about data science, you can read our blogs here
Also, the following are some blogs you may like to read