 Hi, everyone. My name is Xiong Chen and I'm from the University of Illinois at Banner-Champaign. Today, representing my team, Shenyang, Dou, Naveen, who are not here, I'll be introducing multi-stage financial modeling, our package to you. Let's start with some background information. Our package focuses on commodity price. So, commodities such as soybean, corn, cotton, their prices are always affected by different and many factors, such as economy, agriculture, weather, policies, you name it. And you can find those information from different sources as well, such as news media, social media, government sites, and private companies. Since the related data are from different resources, you might have different granularities such as some might be daily, some might be weekly, some might be annual. You might have different formats and the data sets might be dirty. Our package, financial modeling art, can help you read in the data, clean the data, and merge data with different granularities into one combined clean table of data frame. It also provides several data visualizations based on your data. In addition, we also have an auto machine learning pipeline, which helps you tune hyperparameters and pick the best model out of it. Now let's see some examples of the outputs from the package. On the top half, from left to right, you can see a line plots of crop progress data. You can see a correlation plots of expert cells. Then it's a time series plot but with a politic events. Then at last you can see a word cloud of the twits. On the left, there's a sample sequential model generated by our package, and that model gives 71% of the variation of describing future price. We also do a soybean contract dashboard. The dashboard is an interactive way to give you some data visualizations based on the data you upload. It provides time series analysis, Twitter analysis, and stock analysis based on your own preference. You can use this dashboard for data visualization as well as exploring the data sets and getting some idea of future selections and engineering. We recommend you to use it along with our package. So I hope you find our package helpful in some ways. So here our package is on GitHub and you can assess our dashboard using the link given down below with the credentials. Make sure to check it out. Thank you guys so much for watching.