QuantBender

Designing Interest Rate & Currency Swaps with Constraint Programming

From classic comparative advantage to enumerating feasible swap structures via CP-SAT

derivatives

swaps

Quantitative-Finance

constraint-programming

optimization

We revisit three standard structured finance situations (two interest rate swaps and one fixed-for-fixed currency swap) and show how to transform the qualitative comparative-advantage reasoning into an explicit constraint programming model (CP-SAT) that systematically enumerates feasible swap rate configurations while enforcing fairness and intermediary (bank) profit conditions.

DOSSEH AMECK GUY-MAX DESIRE

The Binomial No-Arbitrage Pricing Model

Quantitative-Finance

Stochastic-Calculus

Binomial-Model

This is a proposition of solutions to the exercises in the chapter 1 of the book “Stochastic Calculus for Finance I: The Binomial Asset Pricing Model” by Steven Shreve.

DOSSEH AMECK GUY-MAX DESIRE

Cultivating Your AI Garden: Choosing and Managing the Right Models

AI-STRATEGY

MODEL-SELECTION

RAG-AND-AGENTIC-AI

Learn how to select, evaluate, and optimize AI models for your business needs. Discover the importance of prompts, multi-model strategies, and ongoing governance for successful AI workflows.

DOSSEH AMECK GUY-MAX DESIRE

From Idea to Production: A Practical Guide to Building GenAI Apps

RAG-AND_AGENTIC-AI

MLOps

A concise, practical walkthrough of the GenAI journey—from ideation and model selection to building, deploying, and operating production applications.

DOSSEH AMECK GUY-MAX DESIRE

From Chains to Agents: A Short Tour of LangChain

RAG-AND-AGENTIC-AI

A concise overview of LangChain’s chains, memory, and agents—plus a quick look at a Pandas DataFrame agent.

DOSSEH AMECK GUY-MAX DESIRE

Building Flexible AI Workflows with LangChain Expression Language (LCEL)

RAG-AND-AGENTIC-AI

LCEL

Learn how to use LCEL to create composable, readable AI applications with LangChain. Explore its core concepts, automatic type coercion, and practical examples.

DOSSEH AMECK GUY-MAX DESIRE

LangChain Core Concepts — A Concise Guide

RAG-AND-AGENTIC-AI

A quick overview of LangChain’s core concepts, including language models, chat models, prompt templates, example selectors, and output parsers.

DOSSEH AMECK GUY-MAX DESIRE

Introduction to Generative AI

RAG-AND-AGENTIC-AI

This post is an introduction to Generative AI, a fascinating field of artificial intelligence that focuses on creating new content rather than just analyzing existing data.…

DOSSEH AMECK GUY-MAX DESIRE

Foundation Models and Large Language Models: A Practical Business Overview

RAG-AND-AGENTIC-AI

This article provides a concise, practitioner-focused overview of foundation models (including large language models), their advantages, limitations, adaptation techniques, governance considerations, and strategic adoption patterns for enterprise value creation.

DOSSEH AMECK GUY-MAX DESIRE

Natural Language Processing: From Unstructured Text to Structured Intelligence

RAG-AND-AGENTIC-AI

Practitioner-oriented overview of core Natural Language Processing (NLP) concepts: transforming unstructured language into structured representations for downstream AI applications. Covers preprocessing steps, representative use cases, evaluation, and seminal references.

DOSSEH AMECK GUY-MAX DESIRE

Generative AI in Practice: A Concise Field Primer

RAG-AND-AGENTIC-AI

A streamlined, rephrased summary of core Generative AI concepts distilled from a longer reference guide: foundations, retrieval augmentation, agents, prompting patterns, system architectures, and essential tools— with pragmatic checklists and references for deeper exploration.

DOSSEH AMECK GUY-MAX DESIRE

In‑Context Learning & Prompt Engineering: A Practitioner’s Primer

RAG-AND-AGENTIC-AI

Concise, rephrased overview of in‑context learning and prompt engineering: what they are, why they matter, core components of a robust prompt, strengths, limits, and a practical workflow with references for deeper exploration.

DOSSEH AMECK GUY-MAX DESIRE

LangChain: Streamlining LLM Application Development

RAG-AND-AGENTIC-AI

LANGCHAIN

This article introduces LangChain, an open-source Python framework designed to simplify the development of applications powered by large language models (LLMs). It highlights LangChain’s modularity, extensibility, decomposition capabilities, and integration with vector databases, along with practical applications in content summarization, data extraction, and automated content generation.

DOSSEH AMECK GUY-MAX DESIRE

Advanced Prompt Engineering: Techniques, Tools, and Applications

RAG-AND-AGENTIC-AI

Prompt Engineering

This article summarizes key advanced prompting strategies for large language models (LLMs), explains when to use them, and outlines supporting tooling ecosystems. Techniques covered: zero-shot, one-shot, few-shot, chain-of-thought (CoT), and self-consistency prompting. It also introduces prompt templates and agent-based applications using frameworks such as LangChain.

DOSSEH AMECK GUY-MAX DESIRE

LangChain LCEL Chaining Method: A Modern, Composable Workflow Guide

RAG-AND-AGENTIC-AI

LCEL

Structured, rephrased guide to LangChain Expression Language (LCEL): concepts, sequencing, parallelism, type coercion, templates, and practical runnable chains with Python examples.

DOSSEH AMECK GUY-MAX DESIRE