Page History

...

Background and Methodology 

...

The MSP Finance Team Financial Forecasting app of MSPbots uses Overall Trends and Seasonality to calculate values for forecasting. The following example of a For example, the following seasonality graph illustrates how it is possible to forecast the high price seasonality of commodities corn and soy, where abundant supply during the fall harvest period results in lower prices. This Based on the values in the graph, this period reaches its peak during the summer months.

...

C. With Cyclical and Seasonal Variations                                                       D    D. With Cyclical and Seasonal Variations and Random fluctuations

...

Figures C and D add Seasonal and Random value movements to the trend.

How

...

Actual Gross Margin, Revenue, and Expenses are calculated

...

MSPbots uses a Machine Learning model to automatically calculate and detect Overall Trends and Seasonality. 

To This model uses the following methods to forecast values, this model uses: 

1. Autoregressive Technique - This technique assumes that a set of time series data is dependent on its past values and there is a linear relationship between the current value and its past data. Autoregressive models are used in financial and stock market forecasts and economic modeling. 
2. Fourier Method - This is a method of forecasting which is designed to improve the accuracy of time series forecasting by incorporating a more flexible prior distribution for the trend component. This facilitates more complex and non-linear trends in time series data. This method also incorporates additional parameters to factor in seasonality and is widely used as a forecasting method in industries such as finance, retail, and manufacturing. 

...

1. Gross Margin Forecast 
   Gross Margin is calculated as (Total Revenue - Total COGS) / Total Revenue. Although Revenue and COGS (cost of goods sold) can be modeled separately, we use the calculated value and run it using our model. As of posting, the graph below shows an average 93% accuracy measured by the variance (yellow line) between forecast and actual values over 3 months using sample data.
   
2. Revenue Forecast
   The sample data below plots an average accuracy rate of 84.3% for the overall trend captured over seven months and shows a dip from December 2022 to January 2023.
   

The calculations for this Model is run based on an open-source code granted through this license.