<div> <ul class="breadcrumb"> <li><a href="/">Home</a></li> <li><a href="/diy-platform">DIY Platform </a></li> <li><a href="/diy-platform/app-store-index/">App Store </a></li> <li> Understanding Data For Price Forecasting Applications </li> </ul> </div> # Understanding Data for Price Forecasting Applications Price Forecasting can be treated as both regression as well as time series problem. If in training data we have only two fields date and demand then this can be treated as a time series problem. On the other hand if we have number of features in our data then we will treat it as regression problem. To build a highly accurate price forecasting model for your business, you need to understand what kind of data will be used to train your models. The data we will be discussed here is for B2B but can be genralized to B2C as well. We have come up with a framework that is suitable for most of the business. We have categorized data points into various indicator categories for you to understand what drives price forecasting process in room booking. * Analysis : These are the data points which will represent analysis. |Type|Field Name|Indicator|Description| | ----------- | ----------- |----------- | ----------- | | Number | Current Month Price | Analysis | Price in current month | | Number | Last Month Price | Analysis | Price in last month | | Number | Last Month Demand | Analysis | Demand in last month | * Factors/Events: These are the data points which will represent events occured. |Type|Field Name|Indicator|Description| | ----------- | ----------- |----------- | ----------- | | Number | Rain | Event | Average rain on given date | | Number | Temperature | Event | Average temperature on given date | |String | Week Day | Factor | Name of week day of given date (Generally monday has more demand then sunday)| * Cause: These are the data points which will represent cause. |Type|Field Name|Indicator|Description| | ----------- | ----------- |----------- | ----------- | | Number | Number Of Complaints | Cause | How many complaints have you received from the customer so far | | Number | Number Of Complaints in Last Month | Cause | How many complaints have you received from the customer in last month | | Number | Number Of Complaints in Last Three Month | Cause | How many complaints have you received from the customer in last three month | | Number | Price Changing | Cause | How many times has price changed for your offering so far? | | Number | Price Changing in Last Month | Cause | How many times has price changed in last month| | Number | Price Changing in Last Three Month | Cause | How many times has price changed in last three month| ## Format : CSV Once you prepare the data, make sure it is in CSV format with the headers similar to the above table. You can add more fields to data set when you are ready to build your own ML model.