Data-Analyst Sis

Microbiologist | | Data Analyst

[Data-Analyst Sis @maybhad]

@TheAnalystbro I'm currently building it now. I guess that's the only way to scale

[Data-Analyst Sis @maybhad]

@frontend__fairy Congratulations

[Data-Analyst Sis @maybhad]

@TosinOlugbenga Would you need a Data Analyst by any chance?

[Data-Analyst Sis @maybhad]

@Rita_tyna Portfolio

[Data-Analyst Sis @maybhad]

@Shruti_0810 All

[Shruti Codes @Shruti_0810]

All Paid Courses (Free for First 4500 People)

𝗣𝗮𝗶𝗱 𝗖𝗼𝘂𝗿𝘀𝗲 𝗙𝗥𝗘𝗘 (PART - 1)
1. Artificial Intelligence
2. Machine Learning
3. Prompt Engineering
4. Claude,Chatgpt,Grok
5. Data Analytics
6. AWS Certified
7. Data Science
8. BIG DATA
9. Python
10. Ethical Hacking

(72 Hours only )

To get-
1. Follow me to get DM
2. Like + RT
3. Reply " All "

[Data-Analyst Sis @maybhad]

Can anyone write a good supporting statement for an Analyst role for NHS job application? It will be paid. Kindly reach out.

[Data-Analyst Sis @maybhad]

@claracrocs Red please

[Data-Analyst Sis @maybhad]

Day 5 of building in public.

Today I mapped out five project ideas for my portfolio. But instead of starting with "what tool should I use," I started with "what business problem could I solve?"

Patient no-shows in healthcare. Loan default risk in banking. Employee attrition in HR. Customer churn signals in fintech. Production downtime in oil and gas.

1. Healthcare: Patient No-Show Prediction & Scheduling Optimization Business problem: Clinics lose revenue and waste staff time when patients don't show up for appointments.

What I'd do: Analyze appointment data to identify patterns in no-shows (day of week, lead time, patient demographics, appointment type). Build a dashboard showing no-show rates by category and a simple forecasting model to flag high-risk appointments.

2. Finance / Banking: Loan Default Risk Dashboard Business problem: Banks need to understand which borrower profiles carry the highest default risk to make better lending decisions.

What I'd do: Use a public lending dataset (like Lending Club data) to analyze default rates by income, credit score, loan amount, and purpose. Build an interactive Power BI dashboard that lets stakeholders filter by risk category.

3. HR: Employee Attrition Analysis Business problem: Companies spend thousands replacing employees, but often don't understand why people leave. What I'd do: Use an HR attrition dataset to analyze which departments, tenure ranges, salary bands, and satisfaction scores correlate with turnover. End with clear recommendations on where HR should focus retention efforts.

4. Fintech: Customer Transaction Behavior & Churn Signals Business problem: Fintech companies need to spot users who are becoming less active before they leave the platform entirely.

What I'd do: Analyze transaction frequency, average transaction value, and engagement trends over time. Build a dashboard that flags accounts showing declining activity and segments customers by behavior type.

5. Oil & Gas: Production Efficiency & Downtime Tracking Business problem: Unplanned equipment downtime costs oil and gas companies millions. Operations teams need visibility into which assets underperform and why.

What I'd do: Use production and maintenance data to track output by well or asset, identify downtime patterns, and forecast maintenance needs. Build an operations dashboard with KPIs like uptime percentage, production vs. target, and cost per downtime hour.

Each one is a real problem that a company would actually care about. Each one uses a different combination of Excel, SQL, and Power BI. A couple gives me a reason to bring Python into a real project, finally.

What I'm realizing is that a strong portfolio isn't about how many dashboards you have. It's about whether each project answers a question that matters to someone making decisions.

Now I just have to build the ones I haven't already built. That's the fun part.

#120DaysOfDataWithTina #DataAnalytics #PortfolioBuilding #SQL #PowerBI #Excel

[Data-Analyst Sis @maybhad]

Day 4 of building in public

Did a skills audit across Excel, Power BI, SQL, and Python today. Took an honest look at where I stand and where I want to go.

I'm solid in Excel, Power BI, and SQL. I can work through problems independently and build things that make sense. Python is still early for me, but it's on the roadmap.

What stood out most was the difference between knowing a tool and being able to execute under pressure. I can build dashboards, write queries, and clean data. But I want to get to the point where I can do all of that faster, sharper, and without second-guessing myself.

That's the real goal of this challenge. Not just learning more, but getting more reps in. Moving from "I can figure it out" to "I already know how."

Also, I'm setting up my Medium account today. Planning to use it for longer write-ups on my projects as this challenge moves forward.

Small steps, but they're adding up.

#120DaysOfDatalockedin #DataAnalytics #SkillsAudit #SQL #PowerBI #Excel #pythonlearning

[Data-Analyst Sis @maybhad]

Day 3 of building in public

Went back to a project I built for an interview exercise, a Power BI dashboard analysing call centre performance for an agency. At the time, I thought it was solid. It had six visuals, a slicer, and a clean layout.

Today, I applied the analytics lifecycle properly and found I had skipped most of it. The dataset had 7 data columns. I used 5. The two I ignored are staffing levels and post-call handle time, which turned out to contain the most actionable insights in the entire dataset. There was a clear negative correlation between operator numbers and call desertion rates. In one month, staffing was cut by 68% while demand stayed high, and the desertion rate spiked to 26%. I never saw it because I never looked at the relationship between columns.

I also showed raw abandoned call counts instead of calculating the desertion rate as a percentage. I ignored that half the dataset had missing values in one column. I never framed the analysis around the seasonal business cycle that was explicitly mentioned in the brief.

The gap was not technical. I know how to write a DAX measure. I know how to build a scatter plot. The gap was in my process. I skipped "define the question" and "explore the data" and went straight to "build the visual." That meant I built for the columns I noticed first, not for the questions that mattered most.

The lesson is embarrassingly simple: before you open Power BI, write down what you are trying to answer. Profile every column. Check what relates to what, then build.

A dashboard that describes what happened but never says whether it was good or bad, and never suggests what to do about it, is only doing half the job.
Tomorrow I will start working on rebuilding it properly.

#120DaysOfDatachallenge #DataAnalyticslockedin #PowerBI

[Data-Analyst Sis @maybhad]

@AyanKhann15 Thank you

[Data-Analyst Sis @maybhad]

Day 1 of building in public.

Today I stepped back from building dashboards and did something less exciting but probably more important: I reviewed three real analytics job descriptions and tried to understand what they’re actually hiring for.

I highlighted the skills that keep showing up across roles: SQL extraction, Power BI/Tableau dashboards, Excel for messy datasets, and being able to explain insights to people who don’t care how the query works.

What surprised me is how little “advanced” analytics shows up compared to the basics done well. Most roles aren’t asking for fancy modelling; they’re asking for reliable reporting, clean metrics, and fast problem-solving when the data isn’t perfect.

It also made me realise the difference between “knowing” a tool and being able to deliver with it under pressure. One is confidence. The other is proof.

Tomorrow I’m going to start building a small project that reflects these job requirements instead of random portfolio ideas.

If you’re hiring or building in this space, what’s the one skill you wish more analysts were stronger at?

#powerbi #tableau #SQL #excel #120DaysOfDataWithTina #DataAnalytics

[Data-Analyst Sis @maybhad]

Day 2 of Career Reset.

Today I didn’t build anything flashy, I studied what “good” actually looks like.

I reviewed two strong data analytics portfolios and tried to figure out why they felt more credible than most of the ones I’ve seen. Not just visually, but in the way they communicated the work.

Here’s what stood out as quality criteria:

Each project had a clear problem statement (not just “here’s a dashboard”)

The tools were secondary while the thinking and decisions were the main focus

Projects felt complete: clean structure, clear flow, and easy to navigate

The work showed business context, not just technical steps

Results were explained as if they were written for a real stakeholder

There was evidence of iteration (what changed, what didn’t work, what improved)

Big takeaway: a standout portfolio isn’t about having more projects. It’s about having projects that feel intentional and real.

Tomorrow I’m going to compare my current project ideas against these criteria and start cutting what doesn’t hold up.

What’s the one thing that makes you trust a portfolio immediately?

#DataAnalyticsLockedIn #Powerbi #excel #sql

[Data-Analyst Sis @maybhad]

@AfunlehinAishat @chidirolex @AnalystPlaybook @mharyourwha1 @AL_MEEZANYY @AyanKhann15 @Timsedx Can you please share the dataset in my Dm

[Data-Analyst Sis @maybhad]

@segosco Hello,

Please add me so I can DM you

[Data-Analyst Sis @maybhad]

@qa_gandy I love you baje baje

[Data-Analyst Sis @maybhad]

@Allison_Nuel @jon_d_doe One of the sensible comments on here❤️