Develop forecasts using regressions of sales

Assignment Help Operation Management

Reference no: EM13897082

Rachel's Breakfast Café

Rachel Kirkpatrick thought to herself, "What a waste," as she threw away three bags full of unsold items and spoiled ingredients. "I have to get better at estimating how much food to order and prepare."

Rachel owned and operated a small café that specialized in fresh baked quiches, breakfast casseroles, and breads, as well as ready-made country style breakfasts. The café was open six days a week, and closed on Sundays. Rachel had run her shop for over a year now, and business seemed to be taking off. While she had made a number of operating improvements related to the consistency and quality of her products, she still struggled between two extremes of the same problem. On some days Rachel did not have enough ingredients on hand to satisfy the day's customers. In this case some of the people who expected to get one of her famous quiches were disappointed. Other days Rachel had far too much food on hand. On days like today, Rachel found herself throwing away food because she had vastly overestimated the number of customers she would have.

While it was difficult for Rachel to know exactly how many customers she served each day, she was able to accu- rately track the total dollar value of sales. It seemed to her that her business was growing, but she had not taken the time to see whether the increasing demand was a true trend or just her perception. Based on this perception, Rachel had been placing larger orders with her suppliers of milk, eggs, cheese, and other ingredients each week. Each day Rachel placed orders for supplies online at a nearby gro- cer's Web site, and he delivered each order five days later. As Rachel considered how to improve her forecasts for needed items, she thought about possible factors that caused demand to be greater or smaller each day at her café. Fridays and Saturdays were usually busier than other days. Beyond the weekend effect, she noted that the weather had an impact. On rainy days people were less likely to go out for breakfast. Rachel wondered how she
could use this information to improve her business.

Over the next four weeks Rachel collected the data shown in the following table. The "5 day forecast" column shows the probability of rain (percentage) for the area around Rachel's café, as predicted by the local weather service five days into the future. For example, the table shows a forecasted 10 percent probability of rain on the first Monday in the table.

Thursday	50	50	5684
Friday	20	70	5911
Saturday	60	60	6328
Monday	20	20	4932
Tuesday	15	15	5235
Wednesday	20	50	5862
Thursday	20	20	4862
Friday	10	80	6100
Saturday	60	70	6255

This was the forecast released by the weather service on the Wednesday five days earlier. Since it currently took Rachel five days to receive orders for her supplies, she knew that she would need to have the weather forecast at least this far in advance in order for it to be of use to her. At the same time, she also knew that shorter term forecasts are usually more accurate. So, she also decided to also track the "2 day forecast," that is, fore- casts made two days in advance.

Day	Probability of Rain (%) 5 day forecast	Prob ab oily of Rain (%) 2 day forecast	Total Saks
Monday	10	40	5520
Tuesday	20	30	4320
Wednesday	30	10	4212
Thursday	50	40	4987
Friday	80	80	5545
S attuday	90	90	6023
Monday	60	30	4590
Tuesday	70	30	4733
Wednesday	90	30	4923
Thursday	100	50	4687
Friday	100	100	5988
S aturday	20	70	6132
Monday	10	10	5324
Tuesday	10	10	4526
Wednesday	10	10	5232

Questions

1. Develop forecasts using regressions of sales on each of the series of rain forecasts respectively. Calculate the MFE (bias), MAD, and MAPE for the two forecasting models. Which rain forecast seems to be better at predicting Rachel's daily sales, the five-day forecast or the two-day forecast?

2. How can Rachel make use of the rain forecasts to improve her forecasts of total sales each day? What other changes to her business would she need to make in order to capitalize on this information?

3. How are order lead time and forecasting accuracy related to each other in this case?

4. Plot and visually inspect the sales data. What other suggestions would you give Rachel for improving her sales forecasts? What type of time series model would be appropriate? Why?

Reference no: EM13897082

Questions Cloud

What are key cost advantages of a level production strategy : What are the key cost advantages of a level production strategy over a chase strategy? Of a chase strategy over a level production strategy?

What is the value of the s and op process to an organization : What is the value of the S&OP process to an organization? Why should it be a dynamic process rather than a one-time annual event?

Do modern technologies make the environment more toxic : What is the most serious environmental threat, SW or HW? Why? Give examples of the activities that generate SW or HW in most urban cities.

What are the advantages and disadvantages of zaras methods : What are the advantages and disadvantages of Zara's methods? Would these methods work at a company like C&F? What advice would you give to Bill Smith?

Develop forecasts using regressions of sales : Develop forecasts using regressions of sales on each of the series of rain forecasts respectively. Calculate the MFE (bias), MAD, and MAPE for the two forecasting models.

Poor housing conditions and adverse health outcomes : Is there any association between poor housing conditions and adverse health outcomes? Please justify your position with in-text citations and a min of 250 + words.

Component interface for an emergency control room : Assignment on the Component Interface for an Emergency Control Room

Discuss human health aspects of noise pollution : Discuss human health aspects of noise pollution and indicate noise control measures to achieve quiet in the community. Please provide a min of 250+words and references.

Features of a change management tool : Features of a Change Management Tool

User Account

All Pages