Describe and explain using language that is understood by a technical audience.

By
Responsive Centered Red Button

Need Help with this Question or something similar to this? We got you! Just fill out the order form (follow the link below), and your paper will be assigned to an expert to help you ASAP.

Order Form

Learning Goal: I’m working on a data analytics writing question and need an explanation and answer to help me learn.Exercise 3 (60 marks)700 words (+/- 15%) not counting labels and numbers on graphs AND no more than four A4 sheets in portrait/vertical mode Your Exercise 3 responses should refer to Exercise 2. In addition to this, you may refer to Exercise 1. USE THE EXCEL FILE BELOW TO ANALYSE THE EXERCISE 3 (ONLY USE THE “SOLVER” OPTION IN THE EXCEL FILE)For the model in Exercise 2, given that you have the actual data for the out-of-sample period (you considered the within-sample period to end in January 2021 – but you do have some data for February 2021 and onwards) – discuss your forecasting method, your forecasts, and the business insights from these, using the following steps: Scope (5 marks) (115 words) Application (5 marks) (115 words) Analysis (10 marks) (115 words) Articulation of Issues (10 marks) (115 words) Critique (15 marks) (115 words) Position (10 marks) (115 words)Scope – Explain the model in Exercise 2 by using language that is understood by a non-technical
audience. You will need to critically think about whether you discuss the pre-optimised or post optimised models. – Discussing short term or long term forecasting goals based on the instructions provided or the importance of short term vs. long term forecasting scope on methods used- Then, specifying the “type of time series components” in the data set #2 – Then, describe what model is used in the data set #2, why and the assumptions behind these models- I need to see that you understand that the model being used in data set#2 is a casual model, a quantitative method that is different from the time series methods used in Report 1. Specifically, I need to see that you understand that this is a multiple regression model using “quasi” explanatory variables as predictors of the revenues. Why this model is used instead of other casual models (e.g., regular explanatory variables, autoregressions) Application – Describe and explain how you applied the data and your knowledge to perform the
forecasts in Exercise 2. Describe and explain using language that is understood by a technical audience.
You will need to critically think about whether you discuss the pre-optimised or post-optimised
models. – Explaining that the time index is a quasi variable used to capture the trend component and how it is coded, and why- Explaining that the dummy seasonal variables used to capture the seasonal component and how it is coded, and why- Explaining that the generating process showing a multiple regression equation – Giving examples of how a forecasting equation for specifific monthly period is computed and what the equation meansNote: Copying/showing the mathematical/conceptual formula without being able to explain what they mean re: the above does not show your understanding of the concepts wellAnalysis – A plot of the considered sample (February 2011 – January 2021) from Exercise 2 and the forecasts
(within and out-of-sample) on one chart. You will need to critically think about whether you plot the
pre-optimised or post-optimised models.
A description of the chart and an analysis of your forecast.
Another plot of the actual data that is beyond the considered sample (February 2021 to the present)
and the forecasts.
A description of the chart and an analysis of your forecast. – Analysing how well the forecasts fit the actual data – Showing your analytical thinking of the above re: trend (do they fit the (upward/downward/constant/inconstant/linear/non-linear) trend well?) and seasonality (do they follow the (multiplicative/additive nature of) seasonal peaks and drops well?- Showing your analytical thinking of the above re: any unusual forecasts (i.e. very much over/under forecasted) – particularly the comparison during Feb 21 to July 2022 – create a table summary of errors- Showing your analytical thinking of the above: re: a comparison between within vs. out of sample forecasts- Providing a little introduction to why the out of sample forecasts do not match the actual time series well (i.e. covid-19 impact) and sharply raising the issues of model modifications needed – but do not go into details here (i.e. creating a flow to the next sections)- I look for some sharp comments that there seems to be a mix of additive and multiplicative nature of seasonality in data set #2. Hence, this model does not seem to capture the changes in seasonality type or non-constant trend (for example, observe the original data set and you will see that during the earlier periods, it is multiplicative seasonality but later on it changes to the additive seasonality. Hence, the model which assumes additive seasonality seems to do better from 2016 onwards). This gives an implication for model justifications in terms of using a composite method – you can go into details of this in the later section. Articulation of Issues – Perform the appropriate check/s and test/s – provide some of this evidence.
What are the issues based on your check/s and test/s above?
Note: we have discussed and conducted several check/s and test/s when we are forecasting in this unit
– and it is up to you to determine which checks and tests are appropriate – to determine issues if any.- Describing if the model(s) satisfy the “adequacy” criteria by showing evidence of the “errors” plot* and ACF test of the “errors” and interpreting the errors plot and correlogram. Note that this is not the ACF test of the “actual” time-series data here. *I need to see comments about the error plots for both the time index (for trend) and also the dummy variables (for seasonality).- Articulate why the model(s) is (not) adequate – in the respect of trend and seasonal characteristics e.g., does it adequately capture the multiplicative/additive nature of the seasonality- Describing if the model(s) satisfy the “accuracy” criteria by showing a summary table of errors functions (e.g., MAE, MAPE, MSE, RMSE) Critique – Critically evaluate your model, and critically evaluate the factors you would need to consider when
forecasting in light of recent events.
Compare and contrast alternative models.
In the context of business forecasting, critically think and discuss any other considerations that need
to be taken into account for your forecasts / forecasting to be useful for business purposes.- Critiquing how COVID-19 impacts the turnover of these businesses – Critiquing if there may be any differences – Critiquing the drawbacks of quantitative methods and the needs for judgemental forecasting (i.e. qualitative methods) Position – Consider the marking rubric, to assist you, you should consider:
This is an informed and justified conclusion that draws upon your discussion above. Given all of the
discussion above, state your position regarding the business insights to be obtained by your forecasts,
by referring to the evidence and ideas that you have discussed above.- Showing that you understand what the analysis/articulation/critique mean in terms of implications re: improving the forecasts- I would like to see you provide concrete suggestions on further research needed e.g., Is there a different impact of COVID-19 on different sectors – I would like to see you some discussion on the use of a composite method (multiplicative and additive models) and other qualitative methods e.g., scenario analysis

How to create Testimonial Carousel using Bootstrap5

Clients' Reviews about Our Services