Modeling commodity prices for valuation and hedging of mining projects subjected to volatile markets
Notice bibliographique
Résumé
Duration between discovery of a mineral deposit and delivery of the material (e.g. metal or concentrate) yielded from this deposit to the market can take several years. After the discovery, a feasibility study is conduced to see if the mining operation on this deposit is economically viable. This feasibility study is exposed to two types of uncertainties, which add to risks to the mining project. These are (1) technical risks arising from sparse data (e.g. grade, recovery and geotechnical characterization) and (2) financial risks arising from unknown future events (e.g. commodity price, discount rate and exchange rate). Among the others, commodity price is a significant concern for the executives of mining enterprise. Given that mining products and their derivatives are traded in commodity, stock and future markets, market dynamics are very complex. Furthermore, it is very sensitive to politics of global world and very open to speculation and manipulation as well as demand and supply. In the past, the mining industry witnessed that many mining operations were suspended or ceased due to unresponsiveness to price fluctuations. Project valuation based on log-term price is a quite naive approach at present day. This can jeopardize the financial resources of the investor company. Therefore, the risks associated with commodity price are assessed, quantified, mitigated, diversified or managed. The analysis of commodity prices starts with the study of historical transactions in financial markets. To facilitate the analysis, it is often necessary to convert commodity prices into returns. Then, the next task is to model the distribution of returns using a statistical distribution. One of the main characteristics of the distribution of commodity price returns is that it tends to have excess kurtosis. This can be explained either by a stochastic volatility or jump component in the diffusion equation describing the evolution of prices. For this reason, it is necessary to consider other models than the Geometric Brownian Motion and Mean-Reverting price models when modeling the dynamics of commodity prices. The objective of this thesis is to construct a robust workflow capable of reproducing the observed price dynamics in the commodity markets. With such calibrated models, it is possible to value mining projects or estimate their exposure to market risk. In the first case, the valuation process is made in a risk-neutral framework using a Real Options approach. In the second case, real world probabilities are used to simulate commodity price paths and assess how a mining project may be exposed to market price fluctuations. Following an introduction and a Literature review, the thesis is divided in four additional parts, corresponding to four different publications. In the first publication, the use of robust estimators for the detection and mitigation of outliers is investigated. The paper starts with an overview of multiple linear regression and assess how the model assumptions can be violated. The second part of the paper deals with detecting outliers the Mahalanobis distance. Then robust regression is used to diminish the effects of outliers in mining engineering data including price. The second paper investigates how the dynamics of iron ore future can be modeled with a dynamic linear model. Traditionally, iron ore futures have been traded using long-term commitment contracts. This paper investigates how relatively recent financial instruments such as futures on iron ore can affect the NPV profile of an iron ore project. The third paper deals with the optimization of the parameters in a commodity model using a genetic algorithm. With correctly calibrated parameters, Monte Carlo simulations of commodity spot and futures are performed and an active trading strategy is implemented in an NPV valuation framework. The last publication deals with the choice of the stochastic process when measuring market risk of a mining project.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,002 | 0,005 |
| Méta-épidémiologie (sens strict) | 0,001 | 0,001 |
| Méta-épidémiologie (sens large) | 0,001 | 0,001 |
| Bibliométrie | 0,001 | 0,001 |
| Études des sciences et des technologies | 0,000 | 0,001 |
| Communication savante | 0,003 | 0,002 |
| Science ouverte | 0,001 | 0,001 |
| Intégrité de la recherche | 0,003 | 0,002 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,004 | 0,000 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».