augmento
AUGMENTO
Predictive analytics
Machine Learning
Artificial Intelligence
While doing planning automation, it became clear that the time had come for advanced AI-enabled forecasting solutions to replace widely used statistical methods.
This led to the creation of the Augmento business unit which employs data scientists, data engineers and business process consultants.
We have a very specific work domain. We develop forecasting models using the most progressive machine learning algorithms. These include demand forecasting, replenishment, innovations planning, promotions planning, as well as assistance in adjusting your current planning and S&OP processes to accommodate a ML-enabled forecast.
Machine Learning has opened up a new era of forecasting. It gears businesses up for management by exception when time and resources are focused on what makes a real difference.
OUR SERVICE
Solutions
- Machine Learning-enabled forecasting
- Front-end visualization of model outcomes (forecast) for analysts and business users
Deliverables
- Forecast accuracy growth
- Forecast bias decrease
- Less resource intensive forecasting
Technology
- Multivariate Machine Learning algorithms:
– Gradient Boosting– Neural networks– Random Forest– ArimaX– Ensemble
- Innovation
sales forecast - Promo investments
forecast - Baseline sales
forecast - ML
Forecast - Optimal pricing
forecast - Off shelf
forecast - Promo-sales
forecast
A NEW ERA OF FORECASTING
Univariate
Statistical models
Highly dependent on expertise and availability of responsible people
Multivariate
Machine Learning algorithms
Process any available internal and external data sources to find the best correlations and build an optimal forecast
Managing by exception when it comes to forecasting
FORECAST BASED ON BIG DATA
Actual sales
Trade terms
Promotions
Assortment movements
Customer stocks
Weather
Store openings
Market data
Pricing
Media spend
Other data to feed
Competitive moves
Macroeconomic indicators
Holidays
CORE STAGES OF LAUNCHING AN ML FORECAST
- 1
Data
discovery & preparation~ 4-7 weeks - 2
Model
and process
building~ 8-15 weeks - 3
Integration
and go live~ 3-5 weeks - 4
Technical
supportIndefinite
ACHIEVABLE RESULTS AFTER LAUNCH
~20%
Increased Forecast accuracy
50%
By up to 50% time Efficiency Improvement for planners
S&OP
Simplified Process
CORE STAGES OF LAUNCHING THE MODEL
1
Data & Process discovery
Investigation into all input data available to build the model as well into the current Forecasting and S&OP processes to fit in. Alignment on Project goals and KPIs before the start.
2
Causals engineering
Selection of relevant data inputs (causals) to start building algorithms. Data pre-processing to feed into the model.
3
Algorithms development
Writing scripts for chosen multivariate ML algorithms like Gradient boosting, Random Forest, Neural network etc. Training and testing for stability, bug fixing.
4
Algorithms tournament
“Tournament” – the model picks up the most suitable algorithm for each forecast item so in the end there is an ensemble of various algorithms which make up an integral model.
5
Product segmentation
ML-generated forecast is split into 3 core segments: No touch, Light touch и Heavy touch depending on the need to manually adjust the forecast.
6
Frontend visualization
The model output can be displayed in Domo or any other BI platform via a special dashboard for planners and S&OP managers as well as for business users.
Архитектура решения
Архитектура решения
Нажмите на иконку
ACHIEVABLE ROI OF THE PROJECT
If Forecast accuracy grows by + 10%
Productivity growth
Less manual work:
- Less time to collect data
- Less errors and time spent to correct them
- Less IT involvement
- Less time for forecasting
Higher forecast accuracy => more reliable P&L => higher quality management decisions
More accurate long term forecast => more sustainable production facilities utilization => higher quality CapEx decisions
Higher customer satisfaction: better contract terms, less penalties, stronger negotiation power
Costs optimization
Less out of stock:
- Higher service level + 3%’
- Higher revenue +1%’ (a conservative estimation for highly efficient business)
Less overstock
- Optimized stocks – 25%’
- Less write-offs- 17%’
Leaner production
- Higher OEE (by up to 11% due to a more forecastable production schedule’)
- More sustainable and efficient labor management
‘Based on an internal assessment by Advanced
FREQUENTLY ASKED QUESTIONS
1
How do you prove that a ML-based forecast is better than the existing one?
During the Test stage, followed by Train (model building), we create a forecast and compare it with historical data for a selected period, as well as with an existing statistical forecast that was available at that time. Then after launch, we track accuracy by comparing actual data (e.g. registered inventory) with ML forecast data, created several weeks back (usually 4-6 weeks back).
2
Which are the key requirements for data to build and run the model?
No less than 2 years of historical data, several input causals to feed the model (e.g. sales, promotional spend, inventory, distribution etc.), a reliable future forecast for each causal so the model can generate a quality forecast.
3
Does the model create a total forecast or a baseline forecast?
A total forecast containing all relevant forecast drivers which come out of causal data. The model can also be tuned to generate a cleansed forecast called Baseline.
4
What is the forecast horizon which comes out of the model?
The horizon is directly dependent on a future forecast for each causal. For instance, if a forecast for promo investments is available for the next 3 months, the model will generate a reliable 3-month future forecast.
5
Can the model be based only on a single causal?
Potentially yes, but the potential of multivariate algorithms would be lost. There should at least be historical data for a target forecasting metric (e.g. sales) and data for that single causal, for example, promotional expenses to develop and make the model work.
6
What do you mean by “manage by exception?”
The forecast generated by the model is split into several segments: 1) No touch – this is a forecast (e.g. a sales forecast), which does not require review by forecast specialists; 2) Light touch – a forecast which is recommended to be double-checked by experts; 3) Heavy touch – a forecast which has to be created manually. For example, when it comes to a sales forecast, these are the products which have no historical sales data.
7
Does the model have any limitations?
Historical data (no less than 2 years), as well as a future forecast for all chosen causals, are instrumental in making the model run well. In the case of data insufficiency for certain forecasting items, a “no touch” approach will have to be used for manual correction.
8
How long does it take to launch the model in full?
It depends on the complexity of the brief (e.g. a model for the whole business or a part of it), data accessibility etc. On average, the project takes 4-6 month.
9
What is specific in your approach to one of the big consulting firms like BCG, SAAS have?
First, we deliver an open model, not a black box. This means that after launch, a client can develop and support the model themselves without our involvement. Second, our team of data scientists and project managers have extensive experience in working in planning departments of big multinational companies. Third, a relatively low cost of model development and support. Thanks to a frontend visualization solution like Domo, each business user in a few clicks can understand what the forecast is made of and what the reasons are for all outliers.
10
What involvement from the business you need?
Mainly, a client needs to participate in helping define objectives for the project, reviewing all data available, providing needed access to databases as well as during the go-live stage when change management to existing ways of working and processes needs to be made.