QUANTITATIVE MODELLING
(WEEK 17-18)
Learning Objectives:
➢ Present a particular business problem or opportunity, Quantifiable,
realistic and measurable with sufficient information needed to solve
the problem or address the opportunity using Quantitative Modelling
and Analysis
➢ Analyze the problem or opportunity and perform the phases of
Quantitative Analysis
➢ Formulate Quantitative Model from a description of a problem
➢ Solve the problem/Address the opportunity
➢ Implement/Communicate the result of Computations and Calculations.
Quantitative Modelling
In finance, quantitative modeling is the practice of organizing and
interpreting data sets with mathematical formulas to identify trends in the
broader markets (Urwin, 2025). It is also a process of representing real-
world phenomena, often from the fields of finance, economics, science,
engineering, and other domains, using mathematical and statistical models.
These models are designed to describe, analyze, and predict the behavior of
complex systems, typically involving numerical data (Josshi, 2023).
Importance in Decision Making
● Data Driven
○ Bases decisions measurable data
● Objective and Logical
○ Reduces bias through systematic analysis
● Predictive Power
○ Forecasts outcomes under various strategies
● Efficiency
○ Saves time and resources by identifying optimal solutions
Why use Quantitative Modelling?
Quantitative modeling is essential for forecasting financial trends and
identifying patterns in data sets (Josshi, 2023). It aids effort in exposing
illegal activity to create a safer marketplace and is relevant for tracking
securities prices, customer demand and other reactions within financial
markets. Although quantitative modelling cannot predict everything, it
remains a valuable field for calculating probabilities and helping businesses
avoid unnecessary risks with the most up-to-date financial data (Urwin,
2025).
Types of Quantitative Modelling
1. Descriptive Modelling
Summarizes past data to understand what has happened. These
models help in organizing and interpreting data without making
predictions.
Example: A dashboard report showing monthly sales, customer
demographics, and product preferences using graphs and tables.
Problem: A retailer wants to understand sales performance over the
last year.
Model: Use bar charts and pivot tables to show sales by month,
category, and region.
Outcome: Insights into peak sales periods and best-selling products.
2. Predictive Modelling
Uses statistical and machine learning techniques to forecast
future outcomes based on historical data.
Example: A regression model predicting next month’s sales based on
advertising spend,past sales, and seasonality.
Problem: A company wants to forecast monthly revenue.
Model: Linear regression: Revenue = α + β1(Ad Spend) + β2(Previous
Month Revenue) + ε
Outcome: Predicted revenue helps in budgeting and inventory
planning.
3. Prescriptive Modelling
Recommends specific decisions or actions based on predictions
and objectives, often using optimization and simulation.
Example: A linear programming model to find the optimal number of
products to produce within cost and labor constraints.
Structured Example:
Problem: A factory wants to maximize profit by producing tables (T)
and chairs (C)
Model:
Maximize: Z = 70T + 50C
Subject to:
10T + 5C ≤ 100 (Labor)
20T + 15C ≤ 180 (Wood)
T, C ≥ 0
Outcome: The model suggests producing 5 tables and 10 chairs for
max profit.
Mathematical Modelling
Mathematical (now computational alike) modelling is an iterative
process which goes from the real-life phenomenon to the virtual
mathematical object called the model that produces results in terms of
how it behaves in hypothetical scenarios. These results should be compared
to actual data that were produced by the real-life phenomenon and were not
used to build or infer the model yet. This comparison, which is called model
validation, usually identifies shortcomings or problems in the model,
advocating some model adjustment (Castiglione et al., 2018).
Real Formulat Compute
Proble e
The
Modellin
g
Cycle
REPORT Validate Interpret
Figure 1. Mathematical or computational model. Those need then to
be compared to the real system to be validated so to show the correctness
and even usefulness of the model. If this is not the case, the model is
improved and the whole cycle is repeated
Value of Mathematical Models in Decision-Making
● Effective risk analysis using statistical methods - helps identify
potential issues before they arise.
● Resource allocation and optimization
● Enhances efficiency - helps in streamlining operations and processes,
reduction of costs and improves customer satisfaction.
● Facilitates strategic planning - firms can project trends based on
historical data (Edu Guide, 2025).
Real World Application
In logistics, companies like Amazon use mathematical models to
determine the most efficient delivery routes using algorithms such as
Dijkstra’s shortest path or linear programming for warehouse distribution.
Scenario:
A delivery company needs to deliver to 5 locations using the least
Fuel.
Model Type: Network model
Formulation:
- Nodes = Delivery points
- Arcs = Roads with distances
Objective: Minimize total distance traveled
Constraints: Each delivery point must be visited once
Outcome: Optimal route is calculated using graph theory,
reducing travel cost by 15%.
Accounting Problem Solving using Management Science
Approaches
Refers to solving accounting-related problems (like budgeting,
forecasting, cost control) using quantitative tools such as forecasting
models, variance analysis, linear programming, and decision trees.
Real World Application
A firm uses time series forecasting to project quarterly revenues and
cost-volume-profit (CVP) analysis to make strategic pricing decisions.
Analytical Consolidation
Analytical consolidation is the integration of data from
multiple business functions or subsidiaries to analyze the overall
financial and operational performance. It also refers to the
process of combining data from different departments,systems,
or subsidiaries to provide a unified view of an organization's
financial or operational performance. It involves analysis to
eliminate redundancies, intercompany transactions, and
inconsistencies for better strategic decision-making.
Business Problem Solving
The systematic process of identifying business issues,
analyzing their causes, developing alternatives, and
implementing solutions using a mix of qualitative and
quantitative methods. The process of identifying, analyzing, and
resolving issues that hinder an organization’s growth, efficiency,
or profitability using structured methods.
Management Modelling
This involves creating abstract models to simulate real
business scenarios for planning, forecasting, decision making
purposes, and optimization techniques. These models may use
math, statistics, or software simulations.
References:
Urwin, M. (2025, April 10). What is Quantitative Modelling? Built In.
https://builtin.com/articles/quantitative-modeling?
fbclid=IwZXh0bgNhZW0CMTEAAR6bwLHIKe7jkMEAKMnA_OVK8TS
QHHFINqY7-
FMYNg4gUp3hPloeUwDGlePoiA_aem_zdlPUHFujBsl54AOOw6rxQ
Josshi, K. (2023, November 7). What is Quantitative modeling: Definition,
tools and users. LinkedIn. https://www.linkedin.com/pulse/what-
quantitative-modeling-definition-tools-users-krishna-joshi--gzsvf/
Castiglione, F., Mancini, E., Pedicini, M., & Jarrah, A. S. (2018, January 1).
Quantitative Modelling Approaches. https://doi.org/10.1016/B978-0-
12-809633-8.20454-8
Edu Guide. (2025, February 3). The Practical Applications of Mathematical
Models in Business. Nickzom Academy.
https://www.nickzom.org/blog/2025/02/03/mathematical-models-in-
business/
