Exploring computational finance with Streamlit

Note: nothing herein is financial advice. This article is made only for informative purposes, not to be used for investment decisions.

Introduction

When researching different methodologies in computational finance, I found a lack of tooling that would enable me to interactively play with different parameters and observe the changes in the model's output. While the mathematical formulation is undeniably the fuel behind the models, I find that it sometimes lacks in providing an intuitive understanding that direct interaction with the model mechanisms can offer.

A clear choice as a solution is building a data app in Streamlit. It offers the pythonic…


Beyond the trade-off between transparency and privacy

Source: Unsplash

Technology is (only) a tool

As data product technology matures, its potential to transform the substrate of our social structure does as well.

Through our improved decision-making, it can move us towards higher well-being. Automation can provide more material abundance, less time involved in repetitive tasks, and thus more time for creative expression. To aim towards self-actualization is a modern luxury that most of our ancestors could never even dream of. The essence of our progress has been technological development.

Yet technology is only a tool. Just as fire can both bake a steak but also burn down a house, so can technology be used…


Predicting Ethereum investor profile with AWS SageMaker

Source: Unsplash

TL;DR

This project aims to connect the Ethereum dataset, machine learning, and cloud technologies in a single project. The outcome is an unsupervised ML data product, accessible through a web UI. It predicts the investor profile (cluster) based on the features constructed on-the-fly with the provided Ethereum address and its publicly available data.

The project code is available on Github.


Ecosystem overview for data scientists

Source: Pixabay

Note: nothing herein is financial advice. This article is made only for informative purposes, not to be used for investment decisions.

Key Points

  • Crypto protocols with their native assets provide an open and data-rich asset class with venture-scale economics and advantages of public market liquidity
  • We still don't have established metrics for long-term valuation which provides a window of opportunity
  • There's an active area of research in modeling crypto protocols as complex systems
  • Decomposing the value chain enables an increased number of iterations on a specific idea maze. This speeds up the collective discovery of a product-market fit.
  • Investing in…


From newspapers to crypto-economic networks

Source: Pixabay

TL;DR

The information that we consume determines the decisions that we make both individually and as a collective. The capitalist, market-based economy enables an efficient allocation of resources but often at a price of misaligned market incentives and societal values. There are clear examples of this in our information diet. Can we design a system that leverages the benefits of the existing one while simultaneously provide information curation whose emergent collective behavior aligns with our societal values?

Let's begin.

“A love of nature keeps no factories busy.”
Aldous Huxley

There is a reason why in the dystopian novel Brave New World


Source: Pixabay

The non-scalable tribal collaboration

“Homo sapiens rules the world because it is the only animal that can believe in things that exist purely in its own imagination, such as gods, states, money and human rights.”

Yuval Noah Harari

Human beings are social animals that have for most of our history (up until about 12000 years) evolved in tribes of no more than 150 people. The rapid proliferation of our species was among other things enabled by language through which we were able to create stories. …


From user acquisition spend to MAU

Introduction

Startup = Growth. As growth is clearly the essential characteristic of each startup or scale-up, it’s also important to be able to model it in order to better understand the levers that govern a certain product business model.

The model presented in this post is a result of modeling the business model at BUX so it makes sense to get a glimpse into it. We have a mobile product that enables simple and affordable trading. There are two stages of using the product. The first stage is when a user is in the funBUX stage (user) and trades virtual money…


Will a user become a top-tier customer?

Source: Pixabay

Introduction

In the process of doing the MSc in Data Science program at the University of Amsterdam I was thinking about how to apply the newly acquired knowledge in the industry. Considering how much I previously enjoyed working in a startup environment in various roles, I knew that I would like to continue on a similar path. Fast-forward a couple of months, I was warmly welcomed by the BUX team to do an internship on the topic of using machine learning to predict customer lifetime value. …


Automating interpretable feature engineering

Source: Pixabay

Introduction

This post will demonstrate the effectiveness of automating interpretable feature engineering with Deep Feature Synthesis and applying it to predicting customer lifetime value.

First I will write about the business value of customer lifetime value prediction and extend it into the classification of users into top-tier customers and non-top-tier customers with the definition of each. This will be followed by the machine learning methodology and show the results of how well the pipeline performed on this specific problem.

If you haven’t yet, please read this post by William Koehrsen providing the explanation of DFS before continuing. If you are only…


How well do we retain different segments of our users?

Source: Pixabay

Introduction

A cohort is a group of subjects who share a defining characteristic. We can observe how a cohort behaves across time and compare it to other cohorts. Cohorts are used in medicine, psychology, econometrics, ecology, and many other areas to perform a cross-section (compare difference across subjects) at intervals through time. (source)

In this post, we’ll focus on observing the behavior of users in a product using Jupyter notebooks.

The importance of retention in a product business extends from the previous post, where we simulated product usage data and can be summarized in three numbers:

  • 95% = Difference in cost…

Jan Osolnik

Data Scientist. Tinkering with tinkering

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store