Knowingly or unknowingly, we all take decisions with the help of data almost every day. What does that mean? That means, we all are data analysts in a way and we don’t even know about it.

Today with the help of a very simple real-life example that I myself was doing on a monthly basis, I’ll show you how we can use the data analytics process to take the right decisions using the power of data.

Before starting it, let’s quickly understand the Data Analytics process.

Generally, it’s a 6-step process as shown below:

Ask --> Prepare --> Process --> Analyze --> Share --> Act

ASK: In this step, we ask questions to better understand the problem and its requirements.

PREPARE: In this step, we find the sources from where we can get the data that we need and eventually get that data.

PROCESS: In this step, we process our data to make it analysis-ready or in simpler words, we make data error-free and relevant to our study.

ANALYZE: In this step, we try to find patterns and trends or use the data that we have to get some insights on what direction should we take to reach our result. Here, we document our findings which will be used in further steps.

SHARE: Now after following the above steps, it's important to communicate the findings with the stakeholders or with those who are a part of this process and brainstorm with them on whether to take a certain decision or not.

ACT: This step is very much self-explanatory. Once everything is decided and agreed upon, then what's stopping you from taking the ultimate decision? ACT upon it !!

Now let's select a problem and go through it step-by-step to understand this process practically.

Objective: To show a real-life example where we use data analytics and link it with the data analytics process.

Problem: What to buy & eat to complete my daily protein intake targeted at muscle mass increase?

Before diving into the problem that we need to solve, we need to have the relevant questions that we need to answer which will eventually help us in taking the right decision by further defining the problem and the things needed to achieve the result

This constitutes the first part of the Data Analytics process i.e. Ask/Plan.

Ask/Plan:

Q1) What is my body weight?

Q2) According to my body weight, what is the required/ideal daily intake of protein that I’ll need?

Q3) What are the different sources of protein intake on top of my diet which can bridge the gap between the current existing intake and the required intake?

Now that we have the questions ready, let’s start getting the answers for them. This can be counted in the Prepare portion of the data analytics process.

Prepare:

Let’s suppose my body weight is 60 Kg. As per the general rule of thumb, the recommended protein intake for a person is 1.2 to 1.7 grams of protein per kg of body weight. Let’s take the upper bound of 1.7 for our calculations.

So, a person who weighs about 60 kg, he/she will require a daily protein intake of about (60*1.7 = 102 grams) to cause an increase in muscle mass over a period of time.

Let’s target it in the range of 100-110 grams/day.

We have to define the existing diet to understand the current gap between current and target positions.
Currently, I have only two meals a day i.e. Lunch and Dinner. For lunch, I have (5 Rotis(bread), 1 small bowl of cooked vegetables, 100gm of Curd, and a small bowl of Dal). For dinner, except for 4 Rotis, the rest all is the same.

Calculating the protein intake for Lunch:

5 Roti (5 * 4 = 20gm) [1 Roti = ~4gm of protein]

A small bowl of cooked vegetables (almost negligible)

Dal (1 serving) (5g) [100gm cooked dal = ~5g]

Curd (5g) [100gm curd = ~5g]

Total = 20+5+5 = 30gm

Now since dinner is almost the same (1 roti less), we’ll take it as ~25gm for dinner

CURRENT STATUS OF PROTEIN INTAKE = 30+25= 55gm

We need close to 50gm more protein to reach our target zone.

There can be multiple sources from which we can derive this. For example non-vegetarian sources (egg, chicken, etc.) and vegetarian sources (milk, oats, paneer, whey, etc.)

Now that we have the data points and the options of sources ready, we can move on to the process section of data analytics where we can pick the preferred sources as per preferences and needs.

Process: (I have supposed that the dietary preference is vegetarian)

For the remaining 50gm of protein, let’s add two more meals in a day i.e Breakfast and Evening Snack to distribute this 50 gm into two chunks.

Since a heavy breakfast is recommended and everyone wants to have it quickly, let’s suppose we have it in liquid form. This could possibly be a whey protein shake with milk & oats.

This will contribute around: (Quantity measure is as per my preference. Could vary)

300 ml milk – 10gm of protein

1 scoop of whey protein - ~24gm of protein

30gm of Oats – 5gm of protein

Total = 10+24+5 = 39gm of protein

Remaining = 50-39 = 11 gm of protein

For the remaining 11gm which will go into the accounts of Evening Snack, one can have a Paneer Salad which may require around 50gm of Paneer. This will contribute around:

50gm of Paneer - ~10gm of protein

Veggies added - negligible protein

With this, we arrive at a total of:

Breakfast (39) + Lunch (30) + Evening Snack (10) + Dinner (25) = 104 gm of protein, which will easily suffice our requirement as stated above that was in the range of 100-110 gm of protein/day.

Now, since the data and details are all in place, we need to decide on buying the right reliable brand for extra items that we’ve added i.e. Whey Protein. (I have chosen only whey protein as other items like milk, oats, and paneer are generic and don’t require comparisons as they do not differ a lot).

So, we’ll have to analyze the various options available in the category of whey protein to finalize the final product/brand to be bought. This part comes under the Analysis part of the Data Analysis process.

Analysis:

To start with, we will search the internet for the 5 most popular brands. Once we get it, we will read the reviews on the online marketplaces about them or directly hear from people that we have access to and who have already used it.

There have been many fraudulent products in the markets as well and even some top famous names sometimes could not stand up to their promised numbers on nutritional facts.

For this, we may go to platforms like YouTube where people have shown live tests of the protein content accuracy of these brands. Using the data from these videos we can finalize the brand which we want to buy.

Share:

We are now ready with the product and brand we need to buy to suffice our protein requirement. Now the task is to communicate this with the stakeholders or the team. In this case, it’s the shopkeepers or the online marketplaces. Make them understand what we want and they’ll provide us with it.

Act:

Now, the final step is to take action or in this case, simply buy it. Perform the money transaction required; receive/collect the product and we’re all set.

So, I hope that after going through this example, understanding the process of data analytics would be a piece of cake for you all from now on.

Thanks for reading it till the end.
Stay hungry and keep learning!