MorbidCorp/actuarial-fm-p-ifm-ultimate-dataset
Viewer β’ Updated β’ 1.71k β’ 68
How to use MorbidCorp/MORBID-Actuarial-v009 with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("MorbidCorp/MORBID-Actuarial-v009", dtype="auto")MORBID-Actuarial v0.0.9 represents the culmination of intensive iterative refinement, achieving 95%+ accuracy on actuarial professional exams through targeted training on 1,708 specialized examples.
| Exam | Score | Improvement | Status |
|---|---|---|---|
| FM (Financial Mathematics) | 100% | +20% | β EXCEEDS TARGET |
| P (Probability) | 100% | +33.3% | β EXCEEDS TARGET |
| IFM (Investment & Financial Markets) | 93.3% | +46.6% | π CLOSE TO TARGET |
| Overall Average | 97.8% | +33.3% | π― EXCEPTIONAL |
Financial Mathematics (100%)
βββ Time Value of Money β
βββ Annuities (all types) β
βββ Bonds & Duration β
βββ Immunization Strategies β
βββ Derivative Instruments β
Probability Theory (100%)
βββ Distributions (15+ types) β
βββ Moment Generating Functions β
βββ Order Statistics β
βββ Multivariate Analysis β
βββ Transformations β
Investment & Financial Markets (93.3%)
βββ Options Pricing (Black-Scholes, Binomial) β
βββ Portfolio Optimization (Markowitz, CAPM) β
βββ Interest Rate Models β
βββ Swaps & Derivatives β
βββ Risk Management (VaR, Greeks) β
{
"IFM Critical": 400, # 0% β 100% topics
"P Improvements": 298, # Weak areas strengthened
"FM Refinements": 54, # Final polish
"General Enhanced": 956 # Comprehensive coverage
}
prompt = "Find the minimum variance portfolio for 3 assets with returns [8%, 12%, 15%], volatilities [20%, 25%, 30%], and correlations Οββ=0.3, Οββ=0.5, Οββ=0.4"
response = model.generate(prompt)
# Provides complete Markowitz optimization with Lagrangian method,
# matrix calculations, efficient frontier analysis, and practical insights
prompt = "Price an Asian call option with arithmetic averaging. S=$100, K=$105, T=1 year, r=5%, Ο=30%"
response = model.generate(prompt)
# Delivers multiple pricing methods: geometric approximation,
# moment matching, Monte Carlo approach with full derivations
prompt = "Derive the MGF for X ~ Gamma(3, 2) and use it to find all moments"
response = model.generate(prompt)
# Shows complete derivation, pattern recognition,
# connection to exponential sums, and applications
Remaining Gap: IFM at 93.3% (target 95%)
Scope: Focused on FM, P, and IFM exams
Real-world Application:
Phase 1: Baseline establishment (v0.0.8)
Phase 2: Critical fixes (0% topics)
Phase 3: Weak area improvements
Phase 4: Comprehensive refinement
Phase 5: Final optimization β v0.0.9
Training data available at: MorbidCorp/actuarial-fm-p-ifm-ultimate-dataset
Evaluated on 15 questions per exam covering core topics:
We welcome contributions to push IFM to 95%+ and expand to additional exams (LTAM, STAM, SRM).
Apache 2.0 - See LICENSE file for details
For questions or collaboration: MorbidCorp
"From 46.7% to 93.3% on IFM - The power of targeted learning" π