Posted on

Improving Sentiment Score Accuracy With FinBERT and Embracing SOLID Principles

In a previous lab titled “Building News Sentiment and Stock Price Performance Analysis NLP Application With Python,” I briefly touched upon the concept of algorithmic trading using automated market news sentiment analysis and its correlation with stock price performance. Market movements, especially in the short term, are often influenced by investors’’ sentiment. One of the main components of sentiment analysis trading strategies is the algorithmic computation of a sentiment score from raw text and then incorporating the sentiment score into the trading strategy. The more accurate the sentiment score, the better the likelihood of algorithmic trading predicting potential stock price movements.

In that previous lab, I used the vaderSentiment library. This time, I’ve decided to explore another NLP contender, the FinBERT NLP algorithm, and compare it against Vader's sentiment score accuracy with the intent of improving trading strategy returns.

Posted on

Building News Sentiment and Stock Price Performance Analysis NLP Application With Python

In this tutorial, I will explore a fintech idea that combines news sentiment analysis and stock trading to make news more actionable for algorithmic trading. This tutorial presents a step-by-step guide on how to engineer a solution that leverages market data API and a sentiment score to demonstrate any correlation between news sentiment and stock price performance.

Traders thrive on having instant access to information that enables them to make quick decisions. Consider a scenario where a trader can promptly identify and access news that directly impacts the performance of their stocks, referred to as investor sentiment. However, reading through articles and discerning the content can be time-consuming and may result in missed opportunities. Imagine if traders could receive immediate notifications within their order management software (OMS) whenever a stock they want to trade receives positive media coverage, which could potentially influence the stock price. This idea also presents the opportunity of automating buy/sell decisions by integrating real-time news sentiment scoring into algorithmic strategies. 

Posted on

Solution vs. Software Architecture

In my tenure as a solution architect in financial services working for a global consulting firm, I have often questioned the best way to practice enterprise architecture.  A common challenge that many architecture consultants face is that most client firms insist on using their proprietary enterprise architecture content. I have observed that frequently such architecture content does not always distinguish between the solution and software architecture.

This article is not an academic paper. In this article, I  present my experiences and ideas to help my colleagues better understand the vague differences between two similar but distinct architecture disciplines. At the very least, this article may trigger a conversation via the comments section that may persuade me that I am wrong.

Posted on

The Case for Software Architecture Makeover

A few years ago, a friend of mine shared with me a white paper that he thought would interest me. This paper described the concept of distributed application architecture through small self-contained application components deployed across a larger corporate network. Eager to impress my friend, I put down the article and exclaimed: “I know where this is going, microservices.” He smiled and replied, “Look at the published date.” To my astonishment, the white paper was published in the late ’90s on the subject of the then relatively new technology called Enterprise Java Beans (EJB).

Sometime later, I hosted a technology leadership forum at a major insurance company in New York. One of the key discussion points included emerging technologies, and of course, microservices. I used the “EJB” anecdote with a profound (sarcastic) conclusion that software architecture styles and patterns do not drastically change, but rather evolve, while software reference application architecture based on a particular technology stack has a lifecycle of emerging, mainstream, and legacy.

Posted on

From Architecture to an AWS Serverless POC: Architect’s Journey

Project Context

This year a number of financial services firms have had to comply with a new "401(k)-to-IRA Rollover Advice" fiduciary rule. This rule mandates that wealth managers and broker-dealers must demonstrate "investor's best interest" intent when presenting investment opportunities to their clients.

Many financial services firms with legacy and 3rd party SaaS application landscape face a common challenge of data lineage and data consistency throughout the client onboarding user journey. Throughout this journey, the client’s investment profile is used to put together a proposed investment portfolio and open an investment account. Client On-boarding Business Process