• Use Cases
  • /
  • Agriculture
  • /
  • Daily Wheat Closing Price Prediction

Daily Wheat Closing Price Prediction

Daily Wheat Closing Price Prediction


The price of grain is a major indicator of the overall household life, and changes in price are made depending on various internal and external factors. In this example, we will predict the daily wheat closing price using the time series analysis method based on the data collected from October 4, 2009 to March 12, 2018.

- Daily prediction of grain price
- Exploring the variation in grain prices

Create Model

1. Check Data

[wheat_200910-201803.csv]
- This dataset is composed of opening price, high price, low price, and closing price over 3072 days.
- The target variable 'close' is an continuous value.

2. Build Model |  Create a wheat price prediction model using CLICK AI's time series prediction

2.1 Model Development

[Main Page → Click on 'Create a new project.']

['Adding data' → Upload data file to Click AI.]

[Select uploaded data file from the dataset list → Click on 'Start AI.']

2.2 Model Configuration

[Select your preferred learning type, preferred method, and the value you would like to analyze/predict.]

 - The target variable 'wheat price' is continuous value based on a time series. Select 'Time series prediction' as your learning type.
- To develop a model focused on maximizing its accuracy, select 'with higher accuracy' as your preferred way.
- Set 'close - wheat_200910-201803.csv' as your value you want to predict.
- Click on (?) for more details about each options.

2.3 Data Preprocessing

['Summary' → Select which columns from the data set you would like to use to train the model.]
- The target variable will be automatically unchosen from being used as part of the training data.

[Data Preprocessing → Select which columns you would like to preprocess.]
- If you would like to preprocess data, continue by clicking on 'Preprocessing.'
- You must select a column for 'Time series criteria' before processing a time series prediction model.

[Choose your preferred preprocessing methods and click 'confirm.']

['Data' → View your data file.]

2.4 Model Creation

[After all of the above steps are completed, press the 'Start' button to begin processing the AI model.]

[All of the processed models will appear in the list at the bottom of the page. You may sort the models according to RMSE, errorRate or Mase.]

3. View Details | Identify important factors for your model

- Let's find out the factors that have the biggest impact on the predictions.

[Training Model  9 → Click on 'Details.']
- View details of the [Training Model  9] with the lowest RMSE.
- You may explore through additional details and statistics on the 'Details' page.

[API Connection → You can connect model results through API connections.]
- API sources are available for multiple programming languages.

4. Analyze Data | Analyze features to derive insights from data

[Training Model 9→ Click on 'Analyze']
View data analysis of the [Training Model9] with the lowest RMSE.

[Visualized information such as histograms and distribution charts are available for users.]

5. Predict Data |  Make single or multiple predictions using your model

5.1 Single Prediction
- Predict wheat price for the selected date by entering a specific date.

[Training Model 9→ Click on 'Single prediction']
- Make single predictions using the [Training Model 9] with the lowest RMSE.

[The predicted result(wheat price) is displayed on the right.]
 - If a value is out of range, the value will appear red.

5.2 Collective Prediction 
- Enter data to the downloaded collective prediction template, and run wheat price  predictions for different dates.

[Training Model 9 → Click on 'Collective prediction']
Make collective predictions using the [Training Model 9] with the lowest RMSE.

[Click on 'Download template for prediction' to download the prediction template.]

[Enter values to the prediction template (left), and prepare a prediction data set (right) to feed into the prediction model.]

[Upload the prepared prediction data, and proceed by pressing on 'Next'.]

[Prediction results will be available on a new csv file. The last column displays the prediction results for each date.]
 - Collective prediction may require some time. You can download the prediction results from the notifications tab after completion.

5.3 Auto-Labeling
 - Enter data to the downloaded auto-labeling template, and run wheat price predictions for different dates.
- Auto-labeling prediction will automatically preprocess data as needed.

[Training Model 9 → Click on 'Auto-labeling]
 - Make auto-labeling predictions using the [Training Model 9] with the lowest RMSE.

[Click on 'Download template for prediction' to download the prediction template.]

[Click on 'Download template for prediction' to download the prediction template.]

[Upload the prepared prediction data, and proceed by pressing on 'Next'.]

[Prediction results will be available on a new csv file. The last column displays the prediction results for different date.]
- Auto-labeling prediction may require some time. You can download the prediction results from the notifications tab after completion.

6. Share | Share your AI model API

[Training Model9→ Click in 'Details']

[Sharing your service app]
- The URL link will direct you to shared page of the model.
- Share your model using the URL link.
- Others may have access to your model through the URL link. If somebody uses the model to make predictions, it will be counted from your prediction count.
- 'Analyze' feature offers both explainable AI and visualizations on the shared link.
- You can put your AI model on sale by using the AI store. For details, please check AI 스토어.

Consult with an expert now.

Consult with an expert now.