Housing affordability in Ghana and most parts of the world is no longer a theoretical policy concern, but a measurable economic constraint that directly impacts household welfare, urban productivity, and social stability. International benchmarks generally define housing as affordable if its costs do not exceed 30% of household income. Beyond this threshold, households are forced to make essential expenditures such as food, education, healthcare, savings, and other necessities in exchange for shelter. Although the cost of living has declined as of January 2026, low- and middle-income earners in urban Ghana are still struggling to meet this indicator.
Structurally, it is commendable that other macroeconomic indicators, particularly the exchange rate, have remained fairly stable over the past year. The cost of imported and locally produced building materials and the price of fuel have also been on the decline over the same period. However, recent estimates put the average price of an “affordable” furnished two-bedroom housing unit in Ghana at between $60,000 and $85,000. This price range remains far from typical income levels.
This article argues that persistently high housing costs are not solely due to macroeconomic pressures, but rather are the result of systemic inefficiencies built into the way housing projects are planned, designed, procured, and ultimately delivered. Within this context, the strategic application of artificial intelligence (AI) presents a viable path to reducing cost overruns, material waste and coordination failures across Ghana’s housing delivery value chain.
Why do construction costs remain high?
One of the main reasons for high construction costs is how buildings in Ghana are planned, designed, procured and delivered. This problem continues from budgeting to design to project completion. It is especially difficult to better manage design changes, cost overruns, material waste, and personnel adjustments. Small inefficiencies along the value chain can compound to lead to significant cost increases at the completion of a construction project’s lifecycle. This challenge becomes more apparent when using traditional project management techniques.
Traditional project management techniques rely on subjective expertise, piecemeal data, and manual calculations to make predictions. These methods are inherently prone to error and bias. Although expert involvement and competence can help reduce these errors, there is still a systematic risk that project inputs may be misestimated. This oversight typically results in increased project costs, longer delays, and, in worst cases, stalled construction projects because the actual costs were misestimated during the budget stage. At this point, we introduce AI as an important means to solve the problems highlighted for achieving affordable housing plans.
Use AI for affordable design
Housing affordability is primarily determined at the budget and design stage, with initial cost assumptions shaping downstream project outcomes. Building owners and project managers need to have honest conversations about the funds allocated to housing projects. This is non-negotiable, as subsequent stages of the project depend on the outcome of the discussion. Once you have determined your budget, you will need to utilize the funds allocated to your design. AI-driven design tools can optimize building specifications, safety compliance, and space configurations to meet predefined budget constraints, reducing overdesign and unnecessary material strength. With the right use of AI tools, engineers and architects can design projects that meet the owner’s specifications and adjust material quantities to match actual performance requirements.
This step is critical to achieving our affordable housing goals. As mentioned earlier, small changes in concrete volume, reinforcement, and finishing materials can significantly reduce construction costs. AI-driven recommendation and predictive modeling systems leverage local materials databases to guide designers in selecting the most cost-effective, durable, and readily available materials that support long-term affordability without compromising quality. This is especially important in markets that rely heavily on imported building materials.
Predict and prevent cost overruns
AI-powered applications can also help with more accurate overrun predictions. Project managers and real estate companies can minimize overruns by incorporating past project information into AI systems powered by machine learning algorithms. The key difference between AI systems and traditional manual estimation techniques is that the former can provide sensitivity analyzes that indicate different conditions under which overruns are likely to occur.
This is a proactive approach to planning for contingencies that typically result in unexpected project cost increases. Predictability is also important so that developers and project managers can intervene and adjust specifications, procurement strategies, and construction methods before costs escalate beyond recovery. Insights from predictive modeling can result in fewer errors, fewer delays, and more affordable completed housing projects.
Smarter sourcing and materials management
Ghana’s high construction costs have powerful hidden drivers that drive procurement inefficiencies. AI makes it easier to optimize supplier selection, delivery times, and inventory management. In such an environment, materials can be replenished at the lowest possible price without compromising quality, allowing projects to run smoothly. This helps reduce direct material costs, storage costs, and transportation costs.
Computer vision technology deployed on construction sites using on-site cameras and drones can track material usage in real-time. This technology can detect wasteful patterns that would otherwise go unnoticed. Even for affordable housing projects with low profit margins, even small changes in waste can have a significant impact on the final affordability outcome.
Implications for policy and practice
While I am an advocate of AI in the housing and construction sector, I must admit that the use of AI alone will not eradicate the affordability crisis. To be clear, I believe that AI presents an opportunity for real estate companies and project managers to streamline budgeting, design, supply chain, and delivery of residential projects. This step is a huge leap in the right direction.
Policymakers should also mobilize support for AI adoption by establishing protocols for data standards, procurement guidelines, ethical safeguards, and regulatory approval processes for the use of AI in this area, and by incorporating AI-enabled cost management into public housing programs. Without such measures, the dream of affordable housing will remain abstract, a slumber from which we may never wake up to face reality.
–
Author Eric Joseph Edouam is a PhD researcher and construction executive whose research focuses on artificial intelligence and housing systems, with a particular focus on affordable housing provision in emerging economies.
