sl. Independent thinking.
Data-informed perspectives.
DATA SCIENCE · AI · MARKET RESEARCHPORTFOLIO / 2026

Sebastian Latiphy.

Finding the signal.
Making it matter.

Exploring ideas at the intersection
of data, intelligence, and people.
++
01 — RAW OBSERVATIONSn = 192
A LITTLE CURIOSITY. A LOT OF POSSIBILITIES.✳
Explore the work ↘ SCROLL TO FIND THE SIGNAL001 / 003
01 / THE PORTFOLIOTHREE WAYS OF LOOKING CLOSER

Curiosity, applied.

Data to understand.
Intelligence to explore. Research to connect.

Sample case studies — illustrative projects while the portfolio takes shape.

Customer segmentationFIG. 01
PURCHASE FREQUENCY →3 CLUSTERS ILLUSTRATIVE DATA
DATA SCIENCE01

Beyond the average customer.

Exploring the patterns that separate one customer journey from another.

Pythonscikit-learnClustering
Explore the case study
SAMPLE PROJECT

The question

How could purchasing behavior reveal meaningful customer groups?

The approach

A sample workflow using recency, frequency, and monetary features, standardized before clustering. Compare cluster stability and interpret each group in the original units.

The takeaway

A useful segmentation needs both statistical separation and a clear reason for a business to treat the groups differently.

Illustrative clusters generated for this portfolio preview. No customer data or measured business results are represented.

AI research assistantFIG. 02
SOURCES → CONTEXT → ANSWER ILLUSTRATIVE DATA
ARTIFICIAL INTELLIGENCE02

A shorter path to an answer.

A concept for turning a collection of documents into traceable answers.

PythonRAGEvaluation
Explore the case study
SAMPLE PROJECT

The question

How could a research assistant make its answers easier to verify?

The approach

A proposed retrieval workflow: split documents into passages, retrieve relevant context, then generate answers with references. Evaluate citation support and include an explicit insufficient-evidence response.

The takeaway

The quality of an answer depends on the evidence retrieved and the ability to check its sources, not just its fluency.

Concept case study with an illustrative retrieval diagram. This preview does not call a model or process documents.

Market signal analysisFIG. 03
OBSERVATIONS + UNDERLYING SIGNAL ILLUSTRATIVE DATA
MARKET RESEARCH03

Seeing what’s moving next.

Separating short-term noise from a longer-term shift in demand.

pandasTime seriesResearch
Explore the case study
SAMPLE PROJECT

The question

When does a change in attention become a signal worth investigating?

The approach

A sample analysis combining an indexed interest series with a rolling average. Investigate seasonality, collection changes, and independent evidence before interpreting a sustained shift.

The takeaway

A rising trend is a starting point for research, not proof of market demand or a forecast of future performance.

Synthetic indexed data for demonstration. It is not a real market or a financial forecast.

02 / BEHIND THE WORK✳

A curious mind.
An analytical lens.

I’m Sebastian. My interests sit where data science, artificial intelligence, and market research meet. This is a space for exploring questions, making sense of complexity, and sharing what I learn.

Start with the projects ↗