A finance strategy (CPPI), implemented on Streamlit/Python, deployed on AWS EC2
Stories by Eyup Gulsun
by Eyup Gulsun
3y ago
np.array([Finance, Python, Streamlit, Cloud Platform]) == http://18.219.211.47:8501/ The journey of building a financial web app… In this article, I would like to show you how to design a CPPI (Constant proportion portfolio investment) strategy and publish it on the Internet. The result is http://18.219.211.47:8501/ (much more fun if you open the link on a big screen rather in a mobile browser) Here are the steps. First, let’s remember what CPPI is. DIVERSIFICATION allows you to eliminate specific or idiosyncratic risks. It cannot help you deal with systematic risk as in 20 ..read more
Visit website
Hi there..
Stories by Eyup Gulsun
by Eyup Gulsun
3y ago
Hi there.. I actually did some research about implementing Streamlit on PythonAnywhere, but i remember i saw several comments saying streamlit might partially run on pythonanywhere and that it can generate error when running. So, i chose the Amazon EC2 ..read more
Visit website
Hello Nikhil -
Stories by Eyup Gulsun
by Eyup Gulsun
3y ago
Hello Nikhil - Thanks for the email and the invitation. I am not a frequent writer in the Medium/LinkedIn, but sure I will let you know about the my next post in advance. Best, Eyup ..read more
Visit website
Just rebooted the system.. thnx 4 the heads-up mate!
Stories by Eyup Gulsun
by Eyup Gulsun
3y ago
just rebooted the system.. thnx 4 the heads-up mate ..read more
Visit website
A finance strategy (CPPI), implemented on Streamlit/Python, deployed on AWS EC2
Stories by Eyup Gulsun
by Eyup Gulsun
3y ago
np.array([Finance, Python, Streamlit, Cloud Platform]) == http://18.219.211.47:8501/ The journey of building the web app: http://18.219.211.47:8501/ The goal is to design CPPI (Constant proportion portfolio investment) strategy and publish it on the Internet. The result is http://18.219.211.47:8501/ (please feel free to play with it!) Here are the steps. First, let’s remember what CPPI is. DIVERSIFICATION allows you to eliminate specific or idiosyncratic risks. It cannot help you deal with systematic risk as in 2008 crisis, when systematic risk impacted all the assets simultaneo ..read more
Visit website
Which one is your volatility — Constant, Local or Stochastic?
Stories by Eyup Gulsun
by Eyup Gulsun
4y ago
Which one is your volatility — Constant, Local or Stochastic? Analyzing the path of EURUSD derived from the market vol surface by using the Heston Model There are three main volatility models in the finance: constant volatility, local volatility and stochastic volatility models. Before the stock market crash of 1987, the Black-Scholes (B-S) model which was built on geometric Brownian motion (GBM) with constant volatility and drift was the dominant model. In this model, stock price is the only source of randomness and it can be hedged with the underlying stock with a return distribution as ..read more
Visit website
Beauty of Karger’s algorithm
Stories by Eyup Gulsun
by Eyup Gulsun
4y ago
Karger’s algorithm back in town (with Python code) Beauty of Karger’s algorithm: Randomness of Monte Carlo in Graphs Divide and conquer! A widely used strategy for years in history. But how to divide? Generally, most intuitive way is to look for segments with lowest levels of affinity or links within systems, networks, and even for populations! So, let’s start! Are you ready for dividing and slicing? Let’s start with networks. We like dense networks, otherwise even if a very single edge or wire is disconnected, a large portion of the network can be down — a situation definetely not desired ! T ..read more
Visit website
A classic bedtime story: Cinderella of Neural Networks
Stories by Eyup Gulsun
by Eyup Gulsun
4y ago
Endgame for “AI Winter” How a competition, ImageNet, along with a noisy algorithm, Stochastic Gradient Descent, changed the fate of AI? Picture from The Elders Scroll | SkyrimIn the early 1980s, Winter was coming for Artificial Intelligence (AI) with a period of reduced funding and interest in AI research, which will later be called the “AI Winter”! During this cold-weather period which lasted until the mid-2000s, almost no research paper on Neural Nets was published because of the lost interest in the field. The reason was simple: no effective algorithms had been put forward against the tradi ..read more
Visit website

Follow Stories by Eyup Gulsun on FeedSpot

Continue with Google
Continue with Apple
OR