In this episode, we are going to use Chai GPT to forecast time series using AI. Specifically, we will use the Amazon revenue data to demonstrate the capabilities of Chai GPT. We will upload the data to Chai GPT and ask it to generate a forecast, which will be sent back to us in an Excel file. We will discuss the limitations of Chai GPT and whether it can be used to improve forecasting accuracy. We will also explore the new features coming soon, such as Copilot in Excel, which aims to provide a more efficient integration with Chai GPT.
To begin, I recommend downloading the file provided and practicing along with me. Make sure you have the latest version of Chai GPT (Chai GPT4) and activate the file upload feature in the settings. Once you have uploaded the file, you can ask Chai GPT to generate a forecast for the next five years of Amazon revenue. The generated forecast will be displayed in a graph, showing the exponential growth of Amazon over the past 14 years and the seasonal pattern for Q4.
While Chai GPT is processing the forecast, let’s discuss its limitations. One major concern is data privacy, as we are sending our Excel file to an external company. Some companies have strict policies against using Chai GPT due to data privacy issues. However, there are solutions in development, such as Copilot in Excel, which aims to address these concerns.
Another limitation is the speed of Chai GPT. The processing time can be quite long, and there may be instances where the answer is not correct or multiple solutions are provided. It is important to be patient and try multiple times to get accurate results. Additionally, the integration with Excel is not always efficient, requiring users to switch between Chai GPT and Excel. However, Microsoft is working on improving this integration with features like Copilot in Excel.
Despite these limitations, Chai GPT and AI in general have the potential to revolutionize forecasting and other tasks. The speed of AI development is exponential, and we are just at the beginning of this acceleration. While AI may not take over our jobs completely, it will certainly change the job market. Those who embrace AI and acquire the necessary skills will have more opportunities and higher salaries. On the other hand, those who are not efficient or skilled in AI may face competition, stress, and lower salaries.
My goal is to support the new generation of experts and leaders who can harness the power of AI to transform and improve supply chains and companies. If you want to dive deeper into the forecasting process and become an expert, I offer free methods and tutorials, as well as upcoming workshops. Check the links below the video for more information.
In conclusion, Chai GPT and AI have the potential to enhance forecasting accuracy and efficiency. While there are limitations to consider, such as data privacy and speed, new features like Copilot in Excel aim to address these issues. The future of AI is exciting and full of possibilities, and it is up to us to adapt and embrace this transformative technology.
