Skip to content
S

SiteScapr (On Web & App)

Find Before you build

Created on 28th February 2026

•

S

SiteScapr (On Web & App)

Find Before you build

The problem SiteScapr (On Web & App) solves

Choosing the right location is one of the most critical factors for the success of any business. However, in cities like Kolkata, identifying an optimal location is challenging due to multiple influencing factors such as foot traffic, accessibility, competition, rental costs, infrastructure, and target audience demographics.

Currently, entrepreneurs and businesses rely on fragmented data sources, manual surveys, or intuition, which often leads to inefficient decision-making, increased risk, and financial losses.

There is no unified platform that integrates and analyzes all relevant location-based parameters to provide data-driven recommendations for business setup.

Challenges we ran into

  1. Availability of Reliable Data

One of the major challenges was obtaining accurate and real-world data for factors such as foot traffic, rental costs, and competition.

Public datasets were often incomplete or outdated

Real-time footfall data is not easily accessible without paid APIs or sensors

Different sources provided inconsistent information

👉 Solution Approach:
We used a combination of:

Approximate data (Google Maps popularity, reviews, area type)

Manual assumptions and sample datasets

Scope for future integration of real-time APIs and surveys

  1. Selecting Relevant Parameters

Identifying which factors truly impact business success was challenging.

Too many parameters made the system complex

Too few parameters reduced accuracy

Solution Approach:
We finalized a balanced set of key parameters:

Footfall
Accessibility
Budget
Competition
Infrastructure
These were chosen based on practical relevance and data availability.

  1. Designing the Scoring Formula

Creating a fair and meaningful formula to rank locations was a critical challenge.
Different parameters have different scales and importance
Some need to be maximized (footfall), others minimized (cost, competition)
Assigning weights required careful reasoning

Solution Approach:

Used a weighted scoring model
Normalized values before calculation
Allowed flexibility to adjust weights based on user preference

  1. Building the AI/Data Processing Pipeline

Designing the pipeline to process inputs and generate recommendations was complex.
Integrating multiple data sources
Cleaning and standardizing data
Ensuring smooth flow from input → processing → output

Solution Approach:

Broke the pipeline into stages:

Data Collection
Data Preprocessing
Feature Scoring
Ranking & Output
Kept the system modular for easier upgrades

Discussion

Builders also viewed

See more projects on Devfolio