Tiffin Consulting

digital business transformation

How Many? – BI Intro (2)

Previous article: Introduction – What is the Business Intelligence, a case study.

Next article: How Much? – BI General Question (Part 3)

This is the second part of a general introduction to BI using a case study of a mobile phone store.

How Many? – this relates to the quantity of items handled by the enterprise and and measures are done over fixed periods of time (e.g. monthly, yearly or even since the start of the enterprise).
A lot of enterprise report this data as tabular or bar chart forms, but proper analysis can often reveal much more than what the data seems to represent. For example, here is the number of phones sold by a high street shop on a monthly basis:

Phones Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec Total
Bar 449 447 401 512 435 395 380 390 395 440 410 387 5041
Flip 251 201 145 198 186 176 156 145 136 187 159 128 2068
Touch 346 312 246 346 325 322 303 309 298 305 299 263 3674
Smart 245 235 201 267 232 212 202 198 188 199 176 153 2508
Android 255 267 232 347 287 290 310 315 320 387 349 356 3715
Total 1546 1462 1225 1670 1465 1395 1351 1357 1337 1518 1393 1287 17006
Understanding Business Intelligence with a case study - how many phones
Figure 1 shows a conventional bar chart plot of table 1. Neither the table nor the bar chart is of much use because none of the representation give us any added visual information. The only information one can clearly extract from figure 1 as opposed to table 1, is that certain phone categories outsell others.

Figure 1 shows a conventional bar chart plot of table 1. Neither the table nor the bar chart is of much use because none of the representation give us any added visual information. The only information one can clearly extract from figure 1 as opposed to table 1, is that certain phone categories outsell others.
Figure 2 is the same same data as figure 1 but the visual information is much clearer and straight away we see a trend appearing in the data: April and October are high sale months across all phone categories. There also seem to be a decline in some sales, but this is more difficult to spot from this graph. To reveal this trend, we need to apply a differential analysis. This is shown in figure 3 below.

Understanding Business Intelligence with a case study
Figure 2 is the same same data as figure 1 but the visual information is much clearer and straight away we see a trend appearing in the data: April and October are high sale months across all phone categories. There also seem to be a decline in some sales, but this is more difficult to spot from this graph. To reveal this trend, we need to apply a differential analysis. This is shown in figure 3 below.

The 2nd trend now appears much more prominently in figure 1.3, while all phones show prominent sales in the months of April and October, only Android phones show an increase in sales, all the other categories are in decline.

This result would be the start of an analysis exercise to answer the questions that naturally arise from this conclusion. Why are phone sales in decline, is it a general market trend or specific to the shop? Why are Android phones sales on the increase? Is it a market trend? Is it at the expense of other types of phones? These are some the questions the executive management would want to find answers to. Market data and past years performance of the shop would be required to fully answer these questions.

Understanding Business Intelligence with a case study
Figure 3 shows a decline in some sales, but this is more difficult to spot from the previous graph. To reveal this trend, we need to apply a differential analysis which is what this plot shows.