Data Science Project Portfolio
Project 1 – Stock market prediction
The challenge of the stock price forecast is the most crucial component for companies and equity traders to predict future revenues. A successful and accurate prediction of future stock prices ultimately results in profit maximization. The stock market is one of the major fields that investors are dedicated to, thus stock market price trend prediction is always a hot topic for researchers from both financial and technical domains. In this research, our objective is to build a state-of-art prediction model for price trend prediction, which focuses on short-term price trend prediction. Repo: https://github.com/vasanthkalai/DataScienceProject
Project 2 – COVID-19 Visualization & Prediction
Coronavirus is a family of viruses that are named after their spiky crown. This project aims at exploring COVID-19 through data analysis and projections. We can use models like Support Vector Machine, Polynomial Regression and Bayesian Ridge Regression to predict the values.
Project 3 – Credit Card Fraud Prediction
Credit card fraud happens in different ways, the new technology on contactless payment on the card allows anyone to read the card details with a contactless card reader. Also, when consumers give their credit card details to unfamiliar individuals when a card is lost or stolen. Many techniques have been introduced to detect fraud in credit card transactions. Fraudsters around the world are always looking for new ways to commit fraud. One of the challenges behind fraud detection is that frauds are far less common as compared to legal transactions. With the increasing number of credit card frauds in the financial sector, we are planning to work on this topic for our project. We found the dataset on Kaggle which is being used to build and train our model. As part of this project, we are developing a few models using anonymized credit card transaction data.
Project 4 – Understanding banking crises in Africa
The purpose of this article is to identify the factors associated with the emergence of banking crises from 1860 to 2014 in a large sample of 13 African countries, using a different models of Machine learning and Deep learning. This dataset is a derivative of Reinhart et. al’s Global Financial Stability dataset which can be found online at: https://www.hbs.edu/behavioral-finance-and-financial-stability/data/Pages/global.aspx The dataset will be valuable to those who seek to understand the dynamics of financial stability within the African context.
Project 5 – Work-Life Balance Survey
The objective of this project is to conduct an Exploratory Data Analysis of the survey responses and advance the understanding of work-life balance and its major influencers are. There are two main sections: 1. Data extraction from Google Sheet and preparation 2. Exploratory Analysis (Healthy body, Healthy mind, Expertise, Connection, Meaning)
Project 6 – Predicting customer lifetime value
The primary goal of this work is to build a probabilistic model for forecasting customer lifetime value in non-contractual setting on an individual level. Using the results of this exercise, managers should be able to: 1. Distinguish active customers from inactive customers. 2. Generate transaction forecasts for individual customers. 3. Predict the purchase volume of the entire customer base.
Project 7 – Employee Churn Model
Employee turn-over (also known as “employee churn”) is a costly problem for companies. The true cost of replacing an employee can often be quite large. A study by the Center for American Progress found that companies typically pay about one-fifth of an employee’s salary to replace that employee, and the cost can significantly increase if executives or highest-paid employees are to be replaced. In other words, the cost of replacing employees for most employers remains significant. This is due to the amount of time spent to interview and find a replacement, sign-on bonuses, and the loss of productivity for several months while the new employee gets accustomed to the new role.
Project 8 – Forest Fire Prediction
One of the alarming & common disasters happening in today’s world is forest fires. These disasters are highly damaging to the ecosystem. To deal with such a disaster, a lot of money on infrastructure & controlling and handling is required. We can build a Data Science project using ‘k-means clustering’- it can identify any forest fires hotspots along with the severity of the fire at that particular spot. It can be alternatively used for better resource allocation with the faster response time. Hence, using the meteorological data such as those seasons around which these kinds of fires tragedies are more likely to happen and various weather conditions that worsen them may increase these results’ accuracy levels.
Project 9 – Road Lane Line Detection
Another Data Science project ideas for beginners include a Live Lane-Line Detection Systems built-in Python language. In this project, a human driver receives guidance on lane detections through lines drawn on the road. Not only this, it further refers to which direction the driver should steer their vehicle. This Data Science Project application is vital for the development of driverless cars. Hence, you can also develop an application with the powerful capability to identify a track line through the input images or via a continuous video frame.
Project 10 – Climate Change Impacts on the Global Food Supply
Frequent Climate change and irregularities are big challenging environmental issues. These irregularities in climate divisions are drastically affecting the human lives residing on the Earth. This Data Science Project concentrates on how the climate impact will highly affect global food production worldwide and how much quantification will impact climate change. The main aim of development for this project is to calculate the potentialities on the staple crop productions due to climate change. Through this project, all the implications related to temperatures & precipitation change. It will then be taken into account how much carbon dioxide affects the growth of plants and the uncertainties happening in the climatic conditioning. Hence, this project will largely deal with Data Visualisations. It will also compare the production in various regions at different time zones.