Mc speed up

.github/workflows/CI.yml

@@ -1,22 +1,23 @@
 name: CI
+
 on:
   push:
     branches:
       - master
     tags: ['*']
   pull_request:
   workflow_dispatch:
+
 concurrency:
-  # Skip intermediate builds: always.
-  # Cancel intermediate builds: only if it is a pull request build.
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: ${{ startsWith(github.ref, 'refs/pull/') }}
+
 jobs:
   test:
-    name: Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }}
+    name: CI 
     runs-on: ${{ matrix.os }}
     timeout-minutes: 60
-    permissions: # needed to allow julia-actions/cache to proactively delete old caches that it has created
+    permissions:
       actions: write
       contents: read
     strategy:

README.md

@@ -4,6 +4,7 @@
 
 [![Build Status](https://github.com/aleCombi/Hedgehog.jl/actions/workflows/CI.yml/badge.svg?branch=master)](https://github.com/aleCombi/Hedgehog.jl/actions/workflows/CI.yml?query=branch%3Amaster)
 [![Documentation](https://img.shields.io/badge/docs-stable-blue.svg)](https://alecombi.github.io/Hedgehog.jl/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
 
 ## 📐 Design Overview
 

docs/src/derivatives_pricing_roadmap.md

@@ -64,9 +64,11 @@
 - [x] Ensure full test suite runs via `Pkg.test()`
 - [x] CI: GitHub Actions with coverage and doc build
 - [x] Tag `v0.1.0` and submit to Julia registry
-- [ ] Soft launch: share with trusted peers, hold off on broad announcement
+- [x] Soft launch: annunce on JuliaDiscourse
 
----
+## PHASE 4.5 — Basic Jump support
+- [ ] Merton model with Carr Madan
+- [ ] Merton model with Montecarlo
 
 ## PHASE 5 — Structured Payoffs
 

examples/Project.toml

@@ -4,6 +4,7 @@ BenchmarkTools = "6e4b80f9-dd63-53aa-95a3-0cdb28fa8baf"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 DataInterpolations = "82cc6244-b520-54b8-b5a6-8a565e85f1d0"
 Dates = "ade2ca70-3891-5945-98fb-dc099432e06a"
+DiffEqNoiseProcess = "77a26b50-5914-5dd7-bc55-306e6241c503"
 Distributions = "31c24e10-a181-5473-b8eb-7969acd0382f"
 ForwardDiff = "f6369f11-7733-5829-9624-2563aa707210"
 Hedgehog = "7f16798b-0e18-40de-98af-932948254698"
@@ -14,8 +15,10 @@ Plots = "91a5bcdd-55d7-5caf-9e0b-520d859cae80"
 Pluto = "c3e4b0f8-55cb-11ea-2926-15256bba5781"
 PlutoUI = "7f904dfe-b85e-4ff6-b463-dae2292396a8"
 Polynomials = "f27b6e38-b328-58d1-80ce-0feddd5e7a45"
+ProfileView = "c46f51b8-102a-5cf2-8d2c-8597cb0e0da7"
 Revise = "295af30f-e4ad-537b-8983-00126c2a3abe"
 Roots = "f2b01f46-fcfa-551c-844a-d8ac1e96c665"
+SciMLBase = "0bca4576-84f4-4d90-8ffe-ffa030f20462"
 SpecialFunctions = "276daf66-3868-5448-9aa4-cd146d93841b"
 StochasticDiffEq = "789caeaf-c7a9-5a7d-9973-96adeb23e2a0"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"

examples/mc_heston_euler.jl

@@ -0,0 +1,54 @@
+# Define the vanilla option payoff
+strike = 100.0
+expiry_date = Date(2025, 12, 31)
+payoff = VanillaOption(strike, expiry_date, European(), Call(), Spot())
+
+# Define the Heston model market inputs using positional arguments
+reference_date = Date(2025, 1, 1)
+spot = 100.0
+rate = 0.05
+heston_inputs = HestonInputs(
+    reference_date,
+    rate,
+    spot,
+    1.5,    # kappa
+    0.04,   # theta
+    0.3,    # sigma
+    -0.6,   # rho
+    0.04    # v0
+)
+
+# Create the pricing problem
+problem = PricingProblem(payoff, heston_inputs)
+
+# Generate a vector of seeds for reproducibility
+num_paths = 10_000
+rng = MersenneTwister(42)
+seeds = rand(rng, UInt, num_paths)
+
+# Pricing with Broadie-Kaya (Heston Exact) using Antithetic variance reduction
+mc_exact_method = MonteCarlo(
+    HestonDynamics(),
+    HestonBroadieKaya(),
+    SimulationConfig(num_paths; seeds=seeds)
+)
+solution_exact = solve(problem, mc_exact_method)
+price_exact = solution_exact.price
+
+# Pricing with Euler-Maruyama using Antithetic variance reduction
+mc_euler_method = MonteCarlo(
+    HestonDynamics(),
+    EulerMaruyama(),
+    SimulationConfig(10*num_paths; steps=200, seeds=seeds, variance_reduction=Hedgehog.Antithetic())
+)
+solution_euler = solve(problem, mc_euler_method)
+sample_at_expiry = Hedgehog.get_final_samples(problem, mc_euler_method)
+sde_prob = Hedgehog.sde_problem(problem, mc_euler_method)
+ens = Hedgehog.simulate_paths(sde_prob, mc_euler_method, mc_euler_method.config.variance_reduction)
+
+config = mc_euler_method.config
+dt = sde_prob.tspan[2] / config.steps
+ensemble_prob = Hedgehog.get_ensemble_problem(sde_prob, config)
+normal_sol = StochasticDiffEq.solve(ensemble_prob, EM(); dt = dt, trajectories=config.trajectories)
+
+price_euler = solution_euler.price

examples/montecarlo_benchmark.jl

@@ -0,0 +1,71 @@
+using Revise
+using Hedgehog
+using Dates
+using Printf
+using BenchmarkTools
+using Random 
+
+function test_eur()
+    spot = 100.0
+    strike = 100.0
+    rate = 0.05
+    sigma = 0.20
+    reference_date = Date(2023, 1, 1)
+    expiry = reference_date + Year(1)
+
+    # Create the payoff (European call option)
+    payoff = VanillaOption(strike, expiry, European(), Call(), Spot())
+
+    # Create market inputs
+    market_inputs = BlackScholesInputs(reference_date, rate, spot, sigma)
+
+    # Create pricing problem
+    prob = PricingProblem(payoff, market_inputs)
+
+    trajectories = 5_000
+    mc_exact_method =
+        MonteCarlo(LognormalDynamics(), BlackScholesExact(), SimulationConfig(trajectories))
+    mc_exact_solution = solve(prob, mc_exact_method)
+    @show mc_exact_solution.price
+
+    display(@benchmark solve($prob, $mc_exact_method))
+end
+
+function test_am()
+    @show "american"
+    # Define market inputs
+    strike = 10.0
+    reference_date = Date(2020, 1, 1)
+    expiry = reference_date + Year(1)
+    rate = 0.05
+    spot = 10.0
+    sigma = 0.2
+    market_inputs = BlackScholesInputs(reference_date, rate, spot, sigma)
+
+    # Define payoff
+    american_payoff = VanillaOption(strike, expiry, American(), Put(), Spot())
+
+    # -- Wrap everything into a pricing problem
+    prob = PricingProblem(american_payoff, market_inputs)
+
+    # --- LSM using `solve(...)` style
+    dynamics = LognormalDynamics()
+    trajectories = 10_000
+    steps_lsm = 100
+
+    strategy = BlackScholesExact()
+    config = Hedgehog.SimulationConfig(trajectories; steps=steps_lsm, variance_reduction=Hedgehog.Antithetic()
+    #variance_reduction=Hedgehog.NoVarianceReduction()
+    )
+    degree = 5
+    lsm_method = LSM(dynamics, strategy, config, degree)
+
+    lsm_solution = Hedgehog.solve(prob, lsm_method)
+
+    @show lsm_solution.price
+
+    display(@benchmark Hedgehog.solve($prob, $lsm_method))
+end
+
+test_eur()
+test_am()

examples/montecarlo_exact.jl

@@ -0,0 +1,48 @@
+using Revise, Hedgehog, BenchmarkTools, Dates
+using Accessors
+import Accessors: @optic
+using StochasticDiffEq
+
+# ------------------------------
+# Define payoff and pricing problem
+# ------------------------------
+strike = 1.0
+expiry = Date(2021, 1, 1)
+
+euro_payoff = VanillaOption(strike, expiry, European(), Put(), Spot())
+
+reference_date = Date(2020, 1, 1)
+rate = 0.03
+spot = 1.0
+sigma = 0.04
+
+market_inputs = BlackScholesInputs(reference_date, rate, spot, sigma)
+euro_pricing_prob = PricingProblem(euro_payoff, market_inputs)
+
+dynamics = LognormalDynamics()
+trajectories = 10000
+config = Hedgehog.SimulationConfig(trajectories; steps=100, variance_reduction=Hedgehog.Antithetic())
+strategy = EulerMaruyama()
+montecarlo_method = MonteCarlo(dynamics, strategy, config)
+
+solution_analytic = Hedgehog.solve(euro_pricing_prob, BlackScholesAnalytic()).price
+solution = Hedgehog.solve(euro_pricing_prob, montecarlo_method).price
+
+@show Hedgehog.solve(euro_pricing_prob, montecarlo_method).price
+@show Hedgehog.solve(euro_pricing_prob, BlackScholesAnalytic()).price
+
+law = Hedgehog.marginal_law(euro_pricing_prob, LognormalDynamics(), expiry) #log-marginal law
+log_sample = rand(law, trajectories)
+final_sample = exp.(log_sample) 
+payoff_sample = euro_payoff.(final_sample)
+discount = df(euro_pricing_prob.market_inputs.rate, euro_pricing_prob.payoff.expiry)
+price = discount * mean(payoff_sample)
+
+antithetic_sample = exp.(2 * mean(law) .- log_sample)
+payoff_anti_sample = (euro_payoff.(final_sample) + euro_payoff.(antithetic_sample)) / 2
+price_anti = discount * mean(payoff_anti_sample)
+
+montecarlo_method_exact = MonteCarlo(dynamics, BlackScholesExact(), config)
+solution_exact = Hedgehog.solve(euro_pricing_prob, montecarlo_method_exact).price
+@btime Hedgehog.solve($euro_pricing_prob, $montecarlo_method_exact).price
+@show solution_exact