Top 5 Key Computer Science Concepts for Finance – DataDrivenInvestor

The most essential five: learn about the fundamental concepts incorporated into finance from computer science with the five of these most important ones

Blue Electric Sparks
By Pixabay from Pexels

I have stated in the past that mathematics is the best field of study in academia to apply to any professional tradecraft. Computer Science has had a profound impact on finance, and especially on those who have studied financial engineering. There is a lot of overlap between computer science and mathematics. A few examples of this are set theory [3], which is used in programming to describe data structures; combinatorics [4], which deals with the ways that discrete objects can be combined or arranged; and algorithms, which are sets of steps for completing tasks that can be applied to math problems as well as ones involving computers.

Computer science has created the ecosystem for the development of more sophisticated financial models and investment strategies and made it possible to analyze large amounts of data.

It has various use cases across quantitative development of strategies and compliance measurements across a range of auditing controls.

By Tuesday Temptation from Pexels

My goal with this post is to introduce the elements of computer science, ones I believe to be the five most important, very briefly for finance, and especially for those pursuing financial engineering. For other areas in financial engineering, I will leave links to posts I have previously authored. Please consider checking them out.

Let us get right to it: here are the five:

Close-Up Photo Of A Digital Image

They are the heartbeat of computer science, and their applications and deployments in finance are prominent among developers. Financial engineering generally deals with the design and implementation of algorithms for financial markets. Achieving this may require optimization techniques that (in general) require finding the best solution from among all possible solutions, given some constraints or objective functions to optimize. Financial engineers often need to solve optimization problem formulations arising from portfolio selection and risk management issues.

To get into the technical aspects of implementing financial engineering methods, start with and very much get into learning about the following three algorithms: the Monte Carlo simulation, the Binomial model, and the Black-Scholes model [5][6][7].

A person holding a map
By Daria Shevtsova from Pexels

Many financial models make use of probabilistic assumptions, and a deep foundation in probability is essential. Additionally, statistics provide a way to test those models against real-world data. Consider learning about the following methods and approaches (remember that these are in the context of financial engineering):

— Monte Carlo methods: these are mathematical techniques used to generate random numbers for use in simulations and could be applied to estimate risks and potential rewards associated with investment strategies [8].

— Random variables: a set of possible values from a given probability distribution. It allows for the quantification of uncertainty and risk in financial engineering applications.

— Probability distributions: a mathematical function that describes how likely it is for a random variable to take on certain values.

Also, know about the following:

— Expectation and variance: the expectation (or expected value) of a random variable measures its average behavior over time or over many trials, while variance measures how much spread there is around this average value [9]. In other words, expectation represents the long-term average outcome of repeated experiments, while variance quantifies how much these outcomes fluctuate from one another (or fluctuations from the expected value).

Lighthouse on stony ground at night
By Ave Calvar Martinez from Pexels

AI technologies potentially enable significant improvements in predictive analytics and other forms of decision-making for finance applications. In the land of machine learning, financial engineering is making use of machine learning techniques to automatically improve models or make predictions. As such, a basic understanding of machine learning concepts is becoming increasingly important for financial engineers.

There are three subfields in AI that apply to financial engineering: natural language processing (NLP), machine learning, and deep learning (a subfield itself to machine learning). Please see all of my posts where I have gone into much more detail about the most important methods and algorithms that apply to financial engineering. Nevertheless, it is important to state the intersection of computer science with artificial intelligence. Namely (and avoiding the three subfields specifically here):

— Financial institutions can implement artificial intelligence to analyze user data and predict likely (future) behavior, information that could potentially help such organizations make decisions about products, services, and pricing.

— AI can be applied to develop new financial instruments or optimize existing ones. For instance, a hedge fund could use machine learning algorithms to automatically generate trading strategies based on market data.

— Banks are using chatbots powered by AI to provide better customer service experiences (e.g., answering questions about account balances and transactions). In the future, these bots may also be able to proactively recommend how best to navigate technology solutions offered to the user based on their feedback given to the AI capability.

Brown Wooden Arrow Signed
By Jens Johnsson from Pexels

DLT describes a type of database that allows multiple parties to share access and view or update entries by reducing the requirement for a central administration [10]. Smart contracts can be employed to create financial instruments [11] that could be potentially self-auditable [12]. DLT could provide new ways to securitize assets by creating tokenized versions of traditional asset classes [13].

Person Holding A Compass
By Joshua Woroniecki from Pexels

Cloud computing refers to the ability to access computation resources on demand using the internet or varied computational systems that connect to cloud computing sources. Cloud computing relies on virtualization, which is a key concept in computer science. To expand, the ability to access and use remote resources using the Internet is central to cloud computing. Through the connectivity process, cloud computing involves distributing data and applications across a network of servers, which is a common technique used in computer science. Running and optimizing applications built with financial engineering can benefit from the scalability and flexibility (specific to this, compare it to on-premise solutions) offered by cloud computing.

Small blue backpack on shore of river
By Matheus Bertelli from Pexels

Please share your thoughts with me if you have any edits/revisions to recommend or recommendations on further expanding this topic.

Also, please kindly consider subscribing to my weekly newsletter:

Anil Tilbe

Financial Engineering: My Posts

11 stories

Also, I have written about the following related to this post; they may be of similar interest to you:


1. Tilbe, Anil. (2022, July 24). 10 essential NLP models for financial engineering.

2. Tilbe, Anil. (2022, July 24). Linear algebra for deep learning, simply explained. Towards AI.

3. Fuzzy set theory — and its applications. (n.d.). Retrieved August 8, 2022, from

4. Combinatorics for computer science. (n.d.). Retrieved August 8, 2022, from

5. Fuzzy set theory — and its applications. (n.d.). Retrieved August 8, 2022, from

6. Probability and statistics for the engineering, computing, and physical sciences. (n.d.). Retrieved August 8, 2022, from

7. K.Mitra, Dr. S. (2012). An Option Pricing Model That Combines Neural Network Approach and Black Scholes Formula. Global Journal of Computer Science and Technology.

8. Botev et al. Why the Monte Carlo method is so important today.

9. Quantitative analysis of probabilistic pushdown automata: Expectations and variances. (n.d.). IEEE Xplore. Retrieved August 8, 2022, from

10. A comparative analysis of distributed ledger technology platforms. (n.d.). IEEE Xplore. Retrieved August 8, 2022, from

11. Sillaber, Waltl, Treiblmaier, Gallersdörfer, & Felderer. (2020). Laying the foundation for smart contract development: An integrated engineering process model. Information Systems and E-Business Management, 19(3), 863–882.

12. Broby. (2017, December 5). The financial auditing of distributed ledgers, blockchain and cryptocurrencies. Strathprints.

13. Workie. (n.d.). Distributed ledger technology: Implications of blockchain for the securities industry. Retrieved August 8, 2022, from

Spread the love

Leave a Reply

Your email address will not be published.