fleur-de-lis-github / Asset-Trading-Analysis-Using-Cryptocurrency

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Asset-Trading-Analysis-Using-Cryptocurrency

Spriha Ghosh (1)

Event: Global Hacks Hackathon- Global Hacks is a hackathon aimed toward promoting a higher level of education and diversity in STEM for all students across the world. Our goal is to introduce to students professional APIs and tools to inspire them to launch their own ideas and projects to tackle global problems. By bringing together innovative minds and students with an appetite for knowledge, Global Hacks provides the perfect environment for everyone to succeed and grow.

✒️ https://globalhacks.net/

Theme

Screenshot (1611) Screenshot (1612)

My Approach

Screenshot (1609)

Problem Scenario

Cryptocurrencies are a digital way of money in which all transactions are held electronically. It is a soft currency which doesn’t exist in the form of hard notes physically. Here, we are emphasizing the difference of fiat currency which is decentralized that without any third-party intervention all virtual currency users can get the services. However, getting services of these cryptocurrencies impacts on international relations and trade, due to its high price volatility. There are several virtual currencies such as bitcoin, ripple, ethereum, ethereum classic, lite coin, etc. In our study, we especially focused on a popular cryptocurrency, i.e., bitcoin. From many types of virtual currencies, bitcoin has a great acceptance by different bodies such as investors, researchers, traders, and policy-makers.

Solution

In our empirical analysis, we analyze the short-term predictability of the bitcoin market, leveraging differentmachine learning models on four different prediction horizons. We find that all tested models make statistically viablepredictions. The models are able to predict the binary market movement with accuracies ranging from 50.9% to 56.0%whereby predictive accuracy tends to increase for longer forecast horizons.

We identify that especially recurrentneural networks, as well as gradient boosting classifiers, are well-suited for this prediction task. Comparing featuregroups of technical, blockchain-based, sentiment-/interest-based, and asset-based features shows that, for mostmethods, technical features remain prevalently important. For longer prediction horizons, the relative importanceappears to spread across multiple features (e.g., transactions per second, weighted sentiment), whereby less recenttechnical features become increasingly relevan

Industry Potential

The cryptocurrency market is expected to witness promising growth in the coming years, owing to improved data transparency and independency across payments in banks, financial services, insurance, and various other business sectors. The use of crypto currency across banking industries provides various benefits such as sending and receiving payment transparently and storing customers detail information securely for next purpose.

The global cryptocurrency market size was valued at $1.49 billion in 2020, and is projected to reach $4.94 billion by 2030, growing at a CAGR of 12.8% from 2021 to 2030.

About


Languages

Language:Jupyter Notebook 100.0%