How can you forecast for new projects with limited historical data?

1 Use a top-down approach

A top-down approach means that you start with the big picture and then break it down into smaller components. For example, you can use industry benchmarks, market research, or expert opinions to estimate the total revenue or demand potential for your new project. Then, you can use historical data from similar or existing projects to allocate the revenue or demand across different segments, channels, or regions. This way, you can create a baseline forecast that reflects the overall market conditions and trends.

2 Adjust for uncertainty

Uncertainty is inevitable when you forecast for new projects with limited historical data. You need to account for the variability and risk that may affect your assumptions and estimates. One way to do that is to use scenario analysis, which involves creating different forecasts based on different assumptions or outcomes. For example, you can create a best-case, a worst-case, and a most-likely scenario for your new project, and compare them to see how they affect your budget and cash flow. Another way to adjust for uncertainty is to use sensitivity analysis, which involves changing one or more variables in your forecast and observing how they impact the results. For example, you can test how your forecast changes if the price, volume, or cost of your new project changes by a certain percentage.

3 Use a rolling forecast

A rolling forecast is a type of forecast that is updated regularly and extends for a fixed period of time. For example, you can create a 12-month rolling forecast that is updated every month, and always covers the next 12 months. A rolling forecast can help you forecast for new projects with limited historical data because it allows you to incorporate new information and feedback as you execute your project. It also helps you to adjust your budget and plans accordingly, and to identify and address any gaps or issues in your forecast.

4 Validate your forecast

Validating your forecast means checking the accuracy and reliability of your data, methods, and assumptions. You need to validate your forecast for new projects with limited historical data to ensure that it is realistic and feasible. You can use various techniques to validate your forecast, such as backtesting, cross-validation, or peer review. Backtesting involves comparing your forecast with actual data from the past to see how well it performs. Cross-validation involves splitting your data into training and testing sets, and using the training set to create the forecast and the testing set to evaluate it. Peer review involves asking other experts or stakeholders to review your forecast and provide feedback or suggestions.

5 Communicate your forecast

Communicating your forecast means sharing your results and assumptions with your team, management, or clients. You need to communicate your forecast for new projects with limited historical data to gain support and alignment for your project. You also need to communicate the limitations and uncertainties of your forecast, and how you plan to deal with them. You can use various tools and formats to communicate your forecast, such as dashboards, reports, or presentations. You should also use clear and simple language, charts, and tables to convey your message and highlight the key points.

6 Here’s what else to consider

This is a space to share examples, stories, or insights that don’t fit into any of the previous sections. What else would you like to add?