• C++ Programming for Financial Engineering
    Highly recommended by thousands of MFE students. Covers essential C++ topics with applications to financial engineering. Learn more Join!
    Python for Finance with Intro to Data Science
    Gain practical understanding of Python to read, understand, and write professional Python code for your first day on the job. Learn more Join!
    An Intuition-Based Options Primer for FE
    Ideal for entry level positions interviews and graduate studies, specializing in options trading arbitrage and options valuation models. Learn more Join!

ChatGPT

 
On the surface, it seems odd to assume that a model designed to make accurate predictions about words and sentences without actually understanding their meanings can understand expected gain. But there is an enormous body of research showing that language and cognition are intertwined. An excellent example is seminal research done by scientists Edward Sapir and Benjamin Lee Whorf in the early 20th century. Their work suggested that one’s native language and vocabulary can shape the way a person thinks.
 
On the surface, it seems odd to assume that a model designed to make accurate predictions about words and sentences without actually understanding their meanings can understand expected gain. But there is an enormous body of research showing that language and cognition are intertwined. An excellent example is seminal research done by scientists Edward Sapir and Benjamin Lee Whorf in the early 20th century. Their work suggested that one’s native language and vocabulary can shape the way a person thinks.
Which is the overall best native language to make it easiest to learn math and programming is what I'd like to know. :D

It clearly can't be portuguese haha
 
Betrand Meyer's views



AI in its modern form, however, does not generate correct programs: it generates programs inferred from many earlier programs it has seen. These programs look correct but have no guarantee of correctness. (I am talking about "modern" AI to distinguish it from the earlier kind—largely considered to have failed—which tried to reproduce human logical thinking, for example through expert systems. Today's AI works by statistical inference.)
 
rng.jpg
 
We asked ChatGPT to generate a document on SOLID (OOP design principles).

Useless.
High-tech plagiarism.
Those OO classes are obscene.
 

Attachments

Are there other ChatGPT type programs that are any better? What about that one that helps autocomplete your code while you are coding.
That sounds like an absolute nightmare to me.
It's a form of mental corrosion.
 
Recently built an LLM powered Jupyter environment specifically for quant research. Great to learn, test out ideas and get source code for implementations. Accepting beta testers and can sign up at Atlas Finance if anyone is interested.
Screenshot 2024-08-15 130040.png
 
Recently built an LLM powered Jupyter environment specifically for quant research. Great to learn, test out ideas and get source code for implementations. Accepting beta testers and can sign up at Atlas Finance if anyone is interested.View attachment 53681
Pretty cool will give it a whirl. Anything you want folks to test in particular?
 
A modest proposal. If you someone/anyone have any time ask ChatGPT

"What is the Fichera function and how is it used in combination with Alternating Direction Explicit (ADE) methpd, expeciallly for PDE-based option pricing".

thx

@Paul Lopez
@APalley
@Andy Nguyen
 
A modest proposal. If you someone/anyone have any time ask ChatGPT

"What is the Fichera function and how is it used in combination with Alternating Direction Explicit (ADE) methpd, expeciallly for PDE-based option pricing".

thx

@Paul Lopez
@APalley
@Andy Nguyen
The **Fichera function** is a concept that arises in the context of partial differential equations (PDEs), particularly in boundary conditions related to PDEs in finance and other applied fields. It is used to define appropriate boundary conditions for the problem to ensure well-posedness, especially in domains where the boundary conditions are not straightforward.

### Fichera Function Overview

The Fichera function is typically used in the context of **second-order elliptic PDEs** and helps in determining whether a boundary condition should be Dirichlet (where the value of the solution is specified on the boundary) or Neumann (where the derivative of the solution is specified). This is particularly relevant when dealing with degenerate PDEs, where the coefficients of the PDE may vanish or become unbounded near the boundary of the domain, a common situation in option pricing models like the Black-Scholes equation for certain types of options.

### Use in PDE-Based Option Pricing

In option pricing, PDEs are used to model the evolution of the option's value over time. For instance, the Black-Scholes PDE is a parabolic PDE that describes the price of a European option. The boundaries of the domain for the PDE are often determined by the limits on the price of the underlying asset (e.g., the asset price cannot be negative and usually has an upper limit in practice).

The Fichera function helps in determining how to set the boundary conditions at these limits. For example, for a vanilla option, the boundaries might be set by assuming the option value is zero when the asset price is very low (a Dirichlet condition). However, in more complex situations (like with barrier options or options on assets with lower bounds), the Fichera function can guide whether to impose Dirichlet, Neumann, or a mixed boundary condition, based on the behavior of the PDE near the boundary.

### Alternating Direction Explicit (ADE) Method

The **Alternating Direction Explicit (ADE)** method is a numerical scheme used to solve multi-dimensional PDEs, such as those arising in option pricing. It is a variant of the Alternating Direction Implicit (ADI) method but differs in that it explicitly updates the solution in each direction separately.

#### How ADE Works:
1. **Alternating Directions**: The PDE is split into components that are handled separately. For a 2D problem (e.g., involving both the asset price and time), one direction (e.g., the asset price) is handled first, followed by the other (e.g., time). This splitting simplifies the computation because each step involves solving a simpler problem.

2. **Explicit Updates**: Unlike ADI methods, where implicit steps are used to ensure stability, ADE uses explicit updates. While explicit methods are generally less stable, ADE can be designed to maintain stability under certain conditions (e.g., by choosing appropriate time steps).

### Combination of Fichera Function and ADE in Option Pricing

When using the ADE method for solving PDEs in option pricing, particularly for multi-asset or path-dependent options, the Fichera function can be crucial in accurately specifying boundary conditions. As ADE progresses through its iterations, the boundaries of the domain (e.g., the limits on the underlying asset prices) must be handled correctly to ensure the stability and accuracy of the solution.

The Fichera function is used to determine whether the boundary conditions in the discretized PDE model should be set in a specific way to avoid non-physical solutions (e.g., negative option prices) and to respect the financial interpretation of the boundary (e.g., an option's payoff structure).

In summary:
- **Fichera Function**: Ensures appropriate boundary conditions for PDEs, particularly in degenerate or complex domains.
- **ADE Method**: A numerical method for solving multi-dimensional PDEs by splitting the problem into simpler components and updating them explicitly.
- **Combined Use**: The Fichera function guides the boundary conditions within the ADE method when solving PDEs in option pricing, ensuring that the numerical solution remains stable and accurate.
 
The **Fichera function** is a concept that arises in the context of partial differential equations (PDEs), particularly in boundary conditions related to PDEs in finance and other applied fields. It is used to define appropriate boundary conditions for the problem to ensure well-posedness, especially in domains where the boundary conditions are not straightforward.

### Fichera Function Overview

The Fichera function is typically used in the context of **second-order elliptic PDEs** and helps in determining whether a boundary condition should be Dirichlet (where the value of the solution is specified on the boundary) or Neumann (where the derivative of the solution is specified). This is particularly relevant when dealing with degenerate PDEs, where the coefficients of the PDE may vanish or become unbounded near the boundary of the domain, a common situation in option pricing models like the Black-Scholes equation for certain types of options.

### Use in PDE-Based Option Pricing

In option pricing, PDEs are used to model the evolution of the option's value over time. For instance, the Black-Scholes PDE is a parabolic PDE that describes the price of a European option. The boundaries of the domain for the PDE are often determined by the limits on the price of the underlying asset (e.g., the asset price cannot be negative and usually has an upper limit in practice).

The Fichera function helps in determining how to set the boundary conditions at these limits. For example, for a vanilla option, the boundaries might be set by assuming the option value is zero when the asset price is very low (a Dirichlet condition). However, in more complex situations (like with barrier options or options on assets with lower bounds), the Fichera function can guide whether to impose Dirichlet, Neumann, or a mixed boundary condition, based on the behavior of the PDE near the boundary.

### Alternating Direction Explicit (ADE) Method

The **Alternating Direction Explicit (ADE)** method is a numerical scheme used to solve multi-dimensional PDEs, such as those arising in option pricing. It is a variant of the Alternating Direction Implicit (ADI) method but differs in that it explicitly updates the solution in each direction separately.

#### How ADE Works:
1. **Alternating Directions**: The PDE is split into components that are handled separately. For a 2D problem (e.g., involving both the asset price and time), one direction (e.g., the asset price) is handled first, followed by the other (e.g., time). This splitting simplifies the computation because each step involves solving a simpler problem.

2. **Explicit Updates**: Unlike ADI methods, where implicit steps are used to ensure stability, ADE uses explicit updates. While explicit methods are generally less stable, ADE can be designed to maintain stability under certain conditions (e.g., by choosing appropriate time steps).

### Combination of Fichera Function and ADE in Option Pricing

When using the ADE method for solving PDEs in option pricing, particularly for multi-asset or path-dependent options, the Fichera function can be crucial in accurately specifying boundary conditions. As ADE progresses through its iterations, the boundaries of the domain (e.g., the limits on the underlying asset prices) must be handled correctly to ensure the stability and accuracy of the solution.

The Fichera function is used to determine whether the boundary conditions in the discretized PDE model should be set in a specific way to avoid non-physical solutions (e.g., negative option prices) and to respect the financial interpretation of the boundary (e.g., an option's payoff structure).

In summary:
- **Fichera Function**: Ensures appropriate boundary conditions for PDEs, particularly in degenerate or complex domains.
- **ADE Method**: A numerical method for solving multi-dimensional PDEs by splitting the problem into simpler components and updating them explicitly.
- **Combined Use**: The Fichera function guides the boundary conditions within the ADE method when solving PDEs in option pricing, ensuring that the numerical solution remains stable and accurate.
Thank you very much, Andy!
 
Andy you have to teach me how to use that thing. When I tried it just crashed on me 🤣
I was the first to have resurrected Fichera and ADE and introduced them in computational finance.

ChatGPT is rubbish here: bluffing, misleading and 95% woefully incorrect.
Platitudes galore.
 
Back
Top