Skip links

Elegant Store

Enabling a Large FMCG company with demand forecasting models

UI/UX Design

Data Engg & Analytics

Mobile App

Elegant Store is a 50+ Billion Pound multinational FMCG brand based out of UK. They were looking for a platform that could help them forecast demand for their online e-commerce operations on Amazon, Target and Walmart for the US market. SynctacticAI platform provided this solution by augmenting their existing teams’ initiatives.

Industry

e-commerce

Company size

<100+ Employee

What we did

Objective

Elegant Store is a 50+ Billion Pound multinational FMCG brand based out of UK. They were looking for a platform that could help them forecast demand for their online e-commerce operations on Amazon, Target and Walmart for the US market. SynctacticAI platform provided this solution by augmenting their existing teams’ initiatives.

Data Ingestion

Sales and marketing data would be available on a weekly and monthly basis and needs to be ingested and structured

ML Models

Multiple Demand Forecasting models would need to be trained and evaluated

Dashboard

The model output data would need to be displayed via a dashboard where teams interact with the data

Challenges

Demand forecasting is a key initiative in retail which helps category managers & merchandisers alike to understand customer demand patterns and accordingly stock inventory and make better marketing decisions.

The RB team wants to improve sales on their Amazon, Walmart and Target sites using better demand forecasting. The current demand forecasting provided by amazon does not meet the requirements of the RB team. Hence by fully utilizing the data and the domain expertise present at the RB team, a more robust and accurate demand forecasting model could be arrived at.

Accuracy on basic models
20 %

High variability in product sales

Solution

Data Ingestion

The synctactic platform was deployed within the client’s infrastructure. Data extracts from their SQL server data lake were filtered in PowerBI and the output excel files were directly uploaded to the synctactic platform. The platform automatically parsed the data and structured the data into a time series by aggregating the data into weekly and monthly series.

The data was also partitioned by category, brand and SKU to generate individual time series for the models. This data was then pre-processed and cleaned for any inconsistencies and outliers and the time series statistics like Stationarity, Seasonality and trends were captured.

ML Models

The univariate demand forecasting models were first trained using ARIMA, S-ARIMA, Prophet and LSTM. These were fine- tuned to provide the required accuracy.

Then multivariate models like Random Forest, VAR and Deep Learning were trained to achieve the desired accuracy as well as provide correlation between demand and market spend as well as Allocation %. The Output data was stored on the platform and made available via a single API.

Dashboarding
Synctactic’s Lightweight Application provided the final interface for the category managers to interact with the model data. This made use of the data access API layer and some of Synctactic’s pre-built components for model parameter control. With the Lightweight application deployed, RB’s Team could search for a category, brand or SKU and then define a forecast period for which they would then be able to view a demand forecast in sales and units. This would also have upper and lower bounds for them to consider their planning activities. A what-if scenario component was also provided in the app where the team could input a marketing send and view the affect on demand and vice versa. Similarly it was also enabled for allocation % to check for out-of- stock events.
Predictive Maintenance

The sensors on the truck keep sending vital information on the health of the truck to synctactic. A project was created to analyse this data. Multiple data sources were combined to provide the inputs to the model that could predict a window during which the truck had to be serviced and to prevent breakdowns. This helped the company save a lot on maintenance costs as any problems with the vehicle could be assessed ahead of time.

Driver Assistance systems

The sensor data on the truck along with driver inputs were added as sources to synctactic. These data points were analysed and a model was trained to classify between good and bad driving behaviour. The output of this model was fed back to the driver to suggest speed to maintain, ideal acceleration during stalls and gear shift behaviour. This system helped the company improve driving as well as fuel efficiency of their trucks.

Outcome

With Synctactic AI, the company was able to bring in a data science based approach to look after their operations and hence improve customer satisfaction. They could optimise routes and stick to SLAs and Reduce operational costs by equipping drivers with feedback systems. Synctactic AI provided them a way to leverage a scalable and flexible data infrastructure for all their data science initiatives.

Cost reduction
0 %

Improved team productivity

Recent Work

Launch your product with Arokee

Partner with us for a digital journey that transforms your business ideas into successful, cutting-edge solutions.

This website uses cookies to improve your web experience.