How Data Analytics Can Help To Improve Your Business

Knowing and understanding your operations and the dynamics that affect it, is one of the best ways to achieve a competitive edge in any industry. Market Leaders generally compete with greater intensity and get more done in less time than their competitors. This is no different to the Transport industry where a lack of time, growing competition, volatile fuel pricing, and increased customer demand have made it difficult to sustain profitability. As these challenges become more and more, Transport companies are forced to find more effective solutions to manage their supply chain and logistics operations more efficiently.

By implementing a Data Analytics model transport companies can find an advanced way to be more efficient and to achieve that all important competitive edge. The completed Data Analytics model allows companies to manage processes more efficiently and ensure that important trends are not disregarded. Regardless the industry, Data Analytics will help any company to interpret their current performance from where they will have a better understanding of their operation and to predict their future.

There are several advantages by implementing a Data Analytics strategy but let us first get a better understanding of Data Analytics before we consider some of the advantages.

1. Data Analytics

Simply put, Data Analytics is the analysis of information through data mining. This might sound relatively simple, but the process is much more than simply analysing data but is a fundamental process for effective business improvement.

Data analytics, summarised, can be divided into 3 categories:

• Descriptive analytics - Descriptive analytics involve the analysis of current and historical data or content so that a company can better understand fluctuations that have occurred over a period. This information is generally visualised through a Business Intelligence (BI) application in aspects such as pie charts, bar charts, line graphs, tables, etc.
• Predictive analytics - Predictive analytics comprises various statistical techniques such as data mining, predictive modelling, and machine learning, to analyse current and historical data to make predictions about future or otherwise unknown events. These models capture relationships between dependent and independent variables to allow companies to identify opportunities and risks. 
• Prescriptive analytics - Prescriptive analytics is the third and final component of Data Analytics incorporates both structured and unstructured data and is reliant on Descriptive and Predictive analytics to provide suggestions on the future course of action. It anticipates what, when and why an identified aspect will happen. 

In short, Data Analytics is used to see what is happening currently, predict what will happen and finally adapt and prescribe the best plan for a given set of information. It is within this whole process where Business Intelligence plays a crucial part, mainly as it provides the visualisation of that, that was identified out of the Data Analytics model.

2. Why Business Intelligence and Predictive Analytics are Important in the Data Analytics Process

As specified before Business Intelligence (Descriptive Analytics) form part of the Data Analytics process and are connected. The general believe among experts are that Business Intelligence assist in the management of daily operations whereas data analytics helps companies to plan more efficiently for the future by using Predictive Analytics to project what will happen in the future.

Business Intelligence, in combination with Predictive Analytics, provide companies with a platform to analysis huge amounts of data, monitor day-to-day operational aspects such as key performance indicators and to provide visualised, live, and accurate reports in the form of dashboards. In short, it allows companies to turn awareness in to efficient action.

We are in the era of big data and companies face an overload of data and information with little time to interpret and use the data effectively. It is here where Business Intelligence plays such an important role as it allows a company to monitor trends, identify changes in market conditions, and to improve decision making based on the available information. There are numerous ways that a company can apply Data Analytics and deploy visualisation through Business Intelligence.

I summarised the three Data Analytics phases with some use case examples below:

3. Predictive Analysis

In a recent case study, we were tasked to run a Predictive Analysis for a Collaborative TMS platform in India. Their primary objective is to enable all related stakeholders in the logistics value chain to come together on a common platform and function as a singular entity with the united purpose of providing efficient logistics at the best cost. The aim of the case study was to predict future profit/loss scenarios between the expected freight charges and the actual cost of moving freight between two location.

We performed this analysis taking various service related independent variables (distance, freight volumes, vehicle size and period) into consideration as well as other economic variables (fuel and toll price changes, etc.) that change regularly or annually and that plays a significant role as transporters need to adapt their freight charges based on these changes. 

In running the model, we established that there is a stronger correlation between distance, volume, and the product in comparison to the vehicle type (Tarre Weight). Time, in this case, does not play a significant role in predicting the dependent variables as the freight transported are not seasonal. 

The Predictive Analysis was converted into a dashboard where information could be filtered between the independent variables. This allows the user to establish, for example, what type of vehicle would be the most cost effective for a particular product on a particular route and many other correlation scenarios.

4. Descriptive Analysis

As is the case in any business, Transport Management consists of many functional areas and the possibilities, where Business Intelligence (Descriptive Analysis) are concerned, is endless. Descriptive analytics, as mentioned before, involve the analysis of current and historical data or content so that a company can better understand fluctuations that have occurred over a period. This information is generally visualised through a Business Intelligence application in aspects such as pie charts, bar charts, line graphs, tables, etc.

So many people build meaningful dashboards with their current and historical data indicating trends that are extremely useful for management to make critical decisions. But nowadays we can access so many other sources of data, data that plays a significant role in your business without people even considering bringing this into context with the internal data they have on hand.

Let us touch on a couple of examples to give you an idea of the possibilities that exist to become more profitable:

• Driving Behaviour Risk Management

Driving behaviour is a critical area for any transporter and the impact of this can have a major impact, e.g. financial loss, increased insurance costs, reputational damage, etc. Practically all Transport companies make use of advanced telematics technology but the amount of data and reports that must be analysed can be time consuming and on several occasions be too late.

We have built a Predictive Analysis model by utilising telematics data to analyse driving risk behaviour and score drivers accordingly. This model can be easily utilised and adapted to any telematics data where distance, time, and related driving events such as speeding and other harsh driving events are indicated. The risk can be displayed as a negative risk (High Average % = Poor Driving) or inverted (High Average % = Good Driving)

By running this in a live environment transport companies will be in a far better position to identify drivers who are putting the company at risk early and address their behaviour before it has a major impact on their business. It is also important to point out which aspects in the driving behaviour causes the risk value, for example, speeding, so that corrective action can be applied to address the correct aspect

• Time Related Factors

Time is a critical factor for any transporter and there are many scenarios that can and must be considered so that issues can be identified and addressed. This include aspects such as the time it takes to load, offload, driving time and stoppages, especially unscheduled stops.

In another case study, a courier company had a specific concern with regards to how long their drivers stop and where they stop for longer than required. As with driving behaviour data, telematics data plays a key role in providing the data for this analysis. But telematics data updates at high speeds and the bigger the fleet the more the risk of missing stoppages that exceeds a certain time due to rapidly updating of data

This case therefore required us to not only run a Predictive Analysis but also to build a specific notification so that the company can be notified when stoppage times exceed a certain limit. We provided a simple dashboard indicating vehicles that exceed the specified time, the location, and the time that they have been stationary, immediately once the parameter has been breached. This also included an automatic email to notify the necessary responsible person.

This application has other possibilities and can also be applied as a risk manage notification where vehicles are not allowed to stop on route between loading and offloading. 

• Financial Impact

Every business operates to be profitable and cutting costs are as important as making more sales to grow the company financially. But in a lot of instances there are costs for which the impact is missed as the financial impact is not always known. Excess idling is one such instance where the financial impact is unknown to most. Most companies apply corrective action, by means of training, where fuel consumption on vehicles are higher than what it should be but the focus is around the way the vehicle is driven and the excess idle is sometimes ignored. 

By applying algorithms and taking certain factors into consideration, excess idling can be converted from time to an indicative cost to show the financial impact it has on a business. This cost can also be predicted and forecasted so that a company can plan how to address this cost, be it in days, weeks, months, or years if data is available. 

Predictions and forecasting can be applied to various other financial and operational data that is available and presented in various formats, e.g. a cost or quantities. In another use case we could predict and forecast the litres of fuel required for a transport company that operates seasonally, so that they can budget accordingly. This prediction can also be converted to be displayed as a monetary value and included fuel price changes over the last 18 months and will also adapt if vehicles are added or reduced based on the vehicle type fuel usage.

• Incident Analysis

Predictive Analytics can also play a significant role in other areas such as health and safety, especially in analysing incidents. In another case study we were approach by a manufacturing company that operates a plant with multiple forklifts. They had a problem with increased forklift harsh braking incidents and more importantly, collisions with pedestrians. 

We used their tracking and incident report data to build a simple dashboard with that allowed them to visualise the impact of the data through Business Intelligence. The dashboard included a satellite view of the plant itself and a couple of related graphs detailing simple aspects of the recorded incidents. The information allowed them to analyse the root causes from a completely new perspective. By applying drill down filters, they could drill down into enough variations to determine related variable factors.

5. Prescriptive Analysis Example

As mentioned before in this article, Prescriptive Analysis is reliant on Descriptive and Predictive analytics to provide suggestions on the future course of action. The related companies, in all the use cases specified above, could put action plans in place to reduce their risks and costs. For example, in the incident analysis use case, high frequency event spots and the reasons for it were identified and aspects such as the routes and pedestrian walking areas changed. By simply doing this, harsh braking events were reduced by more than 60% and the balance of events addressed through corrective action.

The above is just a couple of examples of what can be done through effective Data Analytics. Please feel free to contact me should you require more information or assistance with your Data Analytics projects. We will gladly assist you with your requirements analysis, designing and implementation of your Data Analytics projects.