From big banks to the everyday consumer, technology is changing the way we approach finance. Create a project that exemplifies an aspect of financial technology. Whether its data science related or a web/mobile application, the possibilities are endless!
Create a project related to finance. Your project should focus on one of two categories: data science or financial applications. In your Devpost submission, make sure to explain your project's relevance to finance.
Create a project related to data science, whether it be data visualization, machine learning, or predictions and modeling. If you’re not sure where to start with data analysis, here’s an excellent tutorial. You’ll get bonus points if you wrap your project in a user interface or host it on a website!
Visualize findings from a financial dataset. This can involve identifying trends in financial data, visualizing changes in data over time, or simply displaying data in an accessible/intuitive way. Be sure to explain what you found and why it is important. Some tutorials to get started with are:
- Betalyzer Some datasets to use are:
- New York Stock Exchange
- DIJA 30 Stock Time Series
Build a trading algorithm or an algorithm for stock prediction. Trading, very often, comes to analyzing data and making decisions, fast. Machine learning algorithms excel in analyzing data, whatever its size and density. You can design a trading algorithm that leverages historical financial time-series data to make predictions about future stock/asset prices. Machine learning algorithms allow you to rigorously analyze empirical data and estimate the original distribution from which the data were sampled, which can be used to make future predictions. This is also applicable on a smaller scale to identify local trends in financial data. Here are some resources to get started:
- Playground for Trading Algorithms
- Intro to Algorithmic Trading with Heikien Ashi
- Python for Finance: Algorithmic Trading Note: If you are looking for a trading platform, we recommended looking into Quantiacs. It is a free open-source platform that supports Python and MATLAB. Here’s how you can get started.
Perform sentiment analysis on a financial dataset. Sentiment analysis is a form of machine learning that allows an analyst to view at a glance the tone/mood of large sets of text data such as news or financial reviews. It can also provide insight into how a manager reflects their company performance. - Source This information often reflects company performance - lots of bad publicity about a company is a good indication that the company’s stock will soon decrease. One excellent application of sentiment analysis for financial applications would be to use sentiment analysis on social media (e.g. Twitter) data for stock prediction. Some resources to get started are:
- Basic Sentiment Analysis in Python
- Intro to Deep Learning - Sentiment Analysis
- NPL with Python
- Daily News for Stock Market Prediction Dataset
While this area is centered around predicting stock prices, there are other interesting financial datasets that can be analyzed. Credit scores are a good example -- you can build a statistical model to generate credit scores given personal attributes and information. Another good example involves fraud detection -- you can analyze credit card transactions with ML classification algorithms to determine whether a certain transaction is likely to be fraudulent. Here are some resources to get started:
Create an application related to finance. This can be a mobile or web application.
Blockchain is one of the biggest buzzwords in technology right now. However, understanding and investing into the new form of currency can be confusing and overwhelming. Applications can offer simple, easy-to-understand solutions to these problems. For example, you could create an investment application, that shows exchanges and transactions of your crypto currency. You could create an exploration app, that educates the consumer on different crypto currencies. You could also analyze cryptocurrency data, from prices, news, and market information. Some resources to start with are:
According to Forbes, 44% of Americans don’t have enough cash to cover a $400 emergency. Financial Literacy is a prevalent issue in society. The ease and practicality of applications can help increase financial literacy and help consumers make financially smart decisions. For example, a budgeting app can help consumers plan how much they will spend and how much they will save. Another example is monitoring - an application that tracks your credit score and give you suggestions on how to improve it. Insurances and Loans provide another area for financial literacy. Whichever topic you choose, applications can shape the way consumers stay financially stable. Some tutorials to get started with are:
Bots have many use cases in the FinTech industry such as transactional bots that offer consumers finance coaching/advising services, user-friendly transaction search instead of manually searching bank statements, and automated claims processes for insurance purposes. Transactional bots help transform the user experience into a more pleasant process. Markets are constantly active, and bots are an excellent tool to monitor them. One example of this is a facebook messenger bot that notifies you whenever Facebook stock decreases below a certain threshold. Some resources to get started are: