Progressive
Household Profiling
Unlock personalized, data-driven insights that help you tailor energy management systems to every household’s unique needs.
Progressive Household
Profiling Scores
Delivering customer-centric experiences requires contextual knowledge about each individual customer. Our proprietary PHP Service creates detailed, individual profiles for every household in your portfolio. Using cutting-edge algorithms, PHP delivers insights based on available energy data and interactions without having to rely on customer inquiry. This empowers you to build customer profiles dynamically as customers evolve and avoid typical flaws associated with customer surveys such as incomplete datasets and human bias.
All data from the PHP scores is stored into a single household profile and can be used in our Engagement Service to tailor customer messaging at scale.
1 / Motivation Score
Understanding households’ motivation is crucial for recommending energy optimizations. MOOST automatically assesses whether a household looks to optimize for cost, self-sufficiency, ecology or any combination thereof and classifies each attribute with a respective score.
- Does the household prioritize financial savings and cost reduction?
- How important is environmental sustainability to the household?
- How much does the household value independence from the grid?
2 / Single- vs. Multi Person Score
Understanding the number of residents withing a household is key for making comparisons, relate energy consumption behaviors and recommend actions. MOOST scores each household for single- vs. multi-person with respective confidence levels ranging from 0 to 1 (in which 0 represents a single-person household and 1 indicates a multi-person household at 100% confidence respectively).
3 / Residential vs. Commercial Score
Customers may use residential offerings for commercial or hybrid purposes (e.g. farms, small shops, restaurants). Understanding the property’s use has implications for recommending energy optimization actions. MOOST scores each customers’ building on residential vs. commercial usage with respective confidence levels ranging from 0 to 1 (in which 0 represents residential use and 1 indicates commercial use at 100% confidence respectively).
4 / Generation & Consumption Forecasting
Predicting future consumption and generation patterns, proactive load shifting actions and controls can be recommended. MOOST forecasts consumption and generation both on energy and power through advanced algorithms.
5 / Base Load & Base Consumption Detection
Understanding the base load and base consumption is key to recognize activities and propose action. MOOST automatically calculates the base load and base consumption for each household based on power and energy consumption data.
6 / Load Profile
Mapping a holistic view of households’ consumption and generation data is essential for recommending actions to optimize energy efficiency and suggest suitable assets and tariffs. MOOST integrates all metered and synthesized data into a single profile for in-depth analysis.
7 / Consumption Classification
Classifying households’ consumption is key for meaningful comparisons and relatable values in customer education. MOOST automatically classifies each household into clusters based on their consumption levels which are used for peer comparisons on total consumption, base consumption, energy generation, self-sufficiency and self-consumption.
8 / Interaction Analysis
MOOST tracks households’ interactions with notifications from the Recommender System. Each notification is labelled and analyzed for which types of insights, alerts and action advice a household responds to most positively. The data includes a Likes & Dislikes analysis to gain insights into which notifications resonate with the household and refine future recommendations as well as Behavioral Trends to automatically adapt the system to match household preferences and increase engagement.
9 / Load Disaggregation
MOOST has adopted a Non-Intrusive Load Monitoring (NILM) Algorithm developed by the research partner (University of Applied Sciences Lucerne) for detecting key assets, like Heat pump, Electric Vehicle Charging and Solar Production. MOOST is currently working on integrating the NILM algorithm into the standard service offering.
Schedule a free demo
Schedule a demo with our team now or reach out to us at any time via email or phone.
Examples, implementation effort, pricing - we will be happy to answer any of your questions.