Causally Motivated Attribution for Online Advertising
As mentioned in the previous blog post, algorithm-based methodologies for assigning credit to media channels on conversion of a user are becoming more and more popular, replacing archaic methodologies such as first touch and last touch attribution. A paper that goes beyond a regression framework to explain such attributions was presented by Dalessandro et al. which I’ll be going over in the next few sections. Attribution Attribution and Causality Dalessandro et al. propose a counterfactual analysis to produce estimates of the causal effect of advertising channels on user conversion. There are some strict assumptions that have to be met in order to obtain causality from the data, which Dalessandro et al. state as the following: The ad treatment precedes the outcome (conversion of a user) Any attribute that may affect both ad treatment and conversion outcome is observed and accounted for. i.e., there are no unknown variables acting as confounders. Every user has a non-zero probability of receiving an ad treatment. Obviously, in real life scenarios, conditions 2 and 3 are nearly impossible to prove as true in any attribution analysis. It may be possible that an ad campaign is targeted towards a certain demographic, thus violating condition 3, and it may be very possible that confounders such as users’ biases towards certain products and services are unmeasurable quantities. One can see how this would be a challenge. In the interests of brevity, we will not dwell on the mathematical formulation of such an analysis since the practicality of it is dubious. In the next section, I will discuss an approximate causal model that Dalessandro et al. introduce, which recasts the causal estimation problem as a channel importance problem, with better application to real world data. Channel Importance Attribution Before getting into any convoluted equations, I’ll quickly introduce important notation: C={ C1, C2,…Ck } is defined as the set of media channels that have shown ads to a group of people W is a vector of user attributes before being exposed to any ads ( for example, demographics, prior internet searches etc.) Y is a boolean indicating whether or not a user has converted, post exposure to ads (γ = Σ Y, n) is the dataset of n users who have seen the same ads by channels in C, and have the same values W = w, producing γ = Σ Y total conversions S is the set C, excluding Ck (hence a subset of C) ωS,k is the probability that set C begins with the sequence {S, Ck, ….} in some distribution Ω of possible orderings The expectation of channel Ck‘s contribution to Y, over all possible combinations of C, is given as Vk, which can be seen in the equation below: In order to understand this better, consider an example where there are only 2 channels, C1 and C2. Attribution values for the channels can be given as : We can see in this simplified form that the attribution values are affected by how these channels serve their advertisements to the user. It is interesting to note, that in the case of observable ad campaigns, we will already know the order in which channels deliver their ads, making the ωS,k probabilities always 0 or 1. The paper discusses why this observable information can actually be harmful in providing attribution values. Let’s take a look at an example. Consider C = {C1, C2}. Further, let E[γ|{∅}] = E[γ|{C1}] = E[γ|{C2}] = 0, and E[γ|{C1,C2}] = δ >0.. Further, assume that C2 always serves its ads after C1. These assumptions tell us that the individual effects of C1 and C2 cause no conversions among users, but the joint effects of C1 and C2 do lead to some user conversions. Using the formula described above, we can get attribution values as following: Since we have observable probabilities of the sequence in which the channels serve their ads (since C2 always serves after C1), we can note that ω2,1 = 0, and ω1,2=1, giving us the equation in the form above. What is interesting to note now, is the fact that our attribution values tell us that V1 = 0, while V2 = δ. This means, all the credit for the joint effect of C1 and C2 in our example is going to C2, simply due to the fact that C2 serves its ads after C1. This conclusion is harmful, since we can extrapolate this to a general idea that channels that serve their ads later receive greater credit for user conversions ( it basically turns into a last touch attribution model, which is pretty flawed). Dalessandro et al. recognize that using these observable probabilities lead to poor recognition of interaction effects among channels, and instead propose a different way to calculate the quantity ωS,k. The following equation is the crux of their idea : They define Ω as a uniform distribution over all possible orderings of C. They state that ωS,k can now be calculated as : To completely understand this equation would require a very good understanding of Shapley Values, which are a common concept of attribution allocation in game theory. Due to the limited scope of this blog, I will not discuss it here. But if there’s something to take away from the paper’s implementation, it is the fact that observable probability distributions of ωS,k should be ignored in favor of the equation provided by the authors in the equation above.
Data Driven Ad Attribution Models
Marketing today relies on a variety of metrics to gain insight into its efficacy. Given the variety of online and offline channels available to marketers, understanding the impact and interaction of individual channels has become an onerous task, to say the least. Marketers rely heavily on two methods to obtain data-driven insights into the marketing process, Media Mix Modeling (MMM) and Data-Driven Attribution. MMM provides a “top -down” view into the marketing process in order to generate high-level insights into the efficacy of different marketing channels. For example, by looking at data over months or years, MMM can give marketers insight into consumers’ interaction with different marketing media. Attribution models, on the other hand, take a more “bottom-up” approach to the marketing process. These models look at an individual user’s interaction with different media. Since each user is exposed to a combination of marketing channels, the problem lies in ascertaining how much credit to give each marketing channel towards influencing a user’s choice about making a purchasing decision. Historically, marketers have used common attribution models such as last touch (first touch) attribution. Last touch attribution models assign all credit to the last channel (first channel) a user has been exposed to prior to conversion. The flaw in the last touch (first touch) attribution lies in the fact that channels further from (closer to) the conversion funnel are systematically undervalued. To allocate credit more fairly, algorithm-based methodologies have received significant traction in the past decade. In a series of three blogs will introduce three papers that discuss algorithm-based models for media mix modeling and attribution modeling. The dominance analysis approach for comparing predictors in multiple regression (Budescu, 1993) Regression models have become a common way to explore the interaction between revenue and advertising efforts. Budescu introduces a general framework known as dominance analysis that aims to decompose the coefficient of determination (R2). For the sake of simplicity, we will only deal with linear models in this post. Budescu’s work can be extended to any area of research that tries to deal with variable importance. Review of Legacy Methods Various methods have been developed over time to measure the importance of variables. These methods mostly rely on using the coefficients of independent variables from standard linear models to explain variable importance. Let’s look at a standard linear model defined as the following: y=β1 x1+⋯+βi xi+⋯+βp xp+ϵ Let’s denote the coefficient of determination of this model as R2y,X. The vector β= (β1, β2,…..βx) represents the change in the dependent variable y, associated with a unit change in each independent variable, given the other independent variables are left unchanged. Under these constraints, it is reasonable to conclude that the squared coefficients perfectly partition the coefficient of determination, as described in the equation below: R2y,x = ∑pj=1 p2y,xj = ∑pj=1 β2j While this method of using variable coefficients as importance measures is intuitive and appropriate in the case of no intercorrelations between dependent variables, in most real-world applications, dependent variables (advertising channels in this case) have some level of correlation, making this method inappropriate. Dominance Analysis Dominance Analysis compares coefficients of determination of all nested submodels composed of subsets of independent variables with that of the full model. Too much jargon? Let’s take a look at an example. Let’s say we have a total of ‘p’ independent variables in our linear model. We will build 2p-1 models, since these are the total number of subset models that can be created. We will then compute the incremental R2 contribution of each independent variable to the subset model of all other independent variables. Let’s take a scenario where we have 4 independent variables X1 , X2 , X3 and X4. We will build 24-1 models ie. 15 models. These will be 4 models with only one independent variable, 6 models with 2 independent variables each, 4 models with 3 independent variables each, and finally 1 model with all the independent variables. Thus, the incremental R2 contribution for variable X1 for example, is the increase in R2 value when X1 is added to each subset of the remaining independent variables (i.e., the null subset { . } , { X2 } , { X3 } , { X4 } , { X2 , X3 } , { X2 , X4 } , { X3 , X4 } and { X2 , X3 , X4 } ). Similarly, the incremental R2 contribution for variable X2 is the increase in value when is added to each subset of the remaining independent variables (i.e., the null subset { . } , { X1 } , { X3 } , { X4 } , { X1 , X3 } , { X1 , X4 } , { X3 , X4 } and { X1 , X3 , X4 } ). The beauty behind dominance analysis lies in the fact that the sum of the overall average incremental R2 of all independent variables is equal to the R2 of the model with all independent variables (the complete model). This allows easy partitioning of the total coefficient of determination amongst independent variables. An inherent problem with dominance analysis is the lack of computational efficiency. The need to train 2p – 1 models means that the number of models that would have to be trained increases exponentially as the number of independent variables increases. Relative Weights Analysis Another paper, which can be found here, builds on the concept of relative weights analysis as an alternative to dominance analysis. However, relative weights analysis is a fundamentally flawed method of determining attribution and has been debunked, most famously in this paper. The reason I even bring this up, is to forewarn a reader that the theoretical underpinnings of relative weights analysis is dubious, and to recommend dominance analysis as the superior R2 decomposition method.
Closing the Lending Gap with AI and ML- Adjusting to the Neo-Normal
Prior to the Covid-19 pandemic, the financial industry was already evolving at a rapid pace, mainly driven by evolving customer expectations, advancement in technology, and heightened competition from incumbents and new entrants. However, in just a few months, the crisis brought about years of change in the way companies in various sectors perform business. According to a recent McKinsey Global Survey of executives, most companies have accelerated their supply-chain digitation by 3-4 years. The cumbersome and time-consuming Loan origination process Many lenders still use manual and paper-based procedures, which is often a time-consuming process, making it extremely difficult for lending companies to meet their customers’ demands for ever-shorter response times. According to November 2020 Ellie Mae Origination Insight Report Data, the time to close loans has increased to 55 days, up from 54 days in October, which is the biggest concern for companies to satisfy consumers’ evolving demand of expecting much quicker turnaround times in the digital era. Fragmented lending Supply-chain: An age-old need for Digitization Furthermore, financial institutions have many potentials to increase their efficiency and streamline complex processes by digitizing the lending supply chain. Embedding Artificial Intelligence in the ecosystem can subsequently help companies to enhance their overall supply chain performance. It can also help lenders with possible implications across various scenarios regarding time, cost, and ROI. Tackling fragmentation with Digitization Digitization resolves issues arising from fragmentation of delivery as well as sluggishness caused due to legacy loan origination. Moreover, COVID-19 has forced “a change of mindset” from the historically slow pace in digitizing supply-chain activities. Lenders are forced to develop truly end-to-end digital capabilities, from onboarding and application through approval and execution to improve servicing, capacity, and ability to automate underwriting and risk management. AI can be used in various ways in the credit process to make it more agile and efficient. Right from legitimizing a new customer who applies for credit to choosing a suitable credit product or optimizing the credit check, the credit sector’s scope of intelligent data analytics is wide. Not only that, by leveraging AI and ML applications, lending companies can tap into customer experience at the right time with the right offer and can deliver a delightful customer experience. The Road to Business Value – Digital Lending It takes advanced next-gen technology to successfully process mountains of applications to ensure same-day approvals come to fruition. Automation and AI can reduce the time and cost of closing a mortgage and can effectively speed up the time-consuming tasks of gathering, reviewing, and verifying mortgage documents. As a result, AI-backed automation can cut out the mundanity of manual tasks but augment processing with Machine learning can further reduce human interaction. This subsequently reduces time to process and cuts down the probability of errors. AI has moved beyond experimentation to become a competitive differentiator in financial services — delivering a hyper-personalized customer experience, improving decision-making, and boosting operational efficiency. As a result, Financial services companies have no choice but to implement AI and automate the credit value chains. Act now – Change is here! AI has begun to create a tangible impact on the mortgage industry. However, looking beyond the mortgage industry offers a glimpse into the actual magnitude of the AI-enabled disruption still to come. AI technology holds the potential to fundamentally redefine the industry on all levels – challenging traditional cost structures, enabling novel relationships with end customers, and much more. For those, who are yet to embark on their journey towards an artificially intelligent future, the time to act is now. What Next? Tavant recently sponsored Chief Data and Analytics Officers, Financial Services 2021 virtually. Tavant’s leaders Dr. Atul Varshneya, VP – AI, and Vaibhav Sharma, Head – Banktech, discussed ‘Adjusting To The Neo-Normal: Evolving the Art of Credit Decisioning with AI and ML.’ Watch the video here to gain more insights. Reach out to us at [email protected] or visit us here. FAQs – Tavant Solutions How does Tavant use AI and ML to address lending gaps in the new normal?Tavant leverages AI and ML to expand credit access through alternative data analysis, remote verification processes, and adaptive risk models that account for changing economic conditions, helping lenders serve previously underserved markets safely. What lending gap solutions does Tavant offer for the post-pandemic landscape?Tavant provides digital-first lending platforms, contactless verification systems, flexible underwriting models, and real-time economic adjustment algorithms that help lenders adapt to new market realities while maintaining responsible lending practices. What is the lending gap and why does it exist?The lending gap refers to qualified borrowers who can’t access credit due to traditional underwriting limitations, lack of credit history, or geographic constraints. It exists due to rigid criteria, limited data sources, and risk-averse lending practices. How has COVID-19 changed lending practices?COVID-19 accelerated digital lending adoption, increased focus on remote verification, emphasized the need for flexible underwriting, and highlighted the importance of real-time data in assessing borrower creditworthiness. What is alternative credit scoring?Alternative credit scoring uses non-traditional data sources like utility payments, rent history, bank transaction patterns, and employment records to assess creditworthiness for borrowers with limited traditional credit history.
Tavant Sponsors CDAO FS Live 2021
Tavant is participating at CDAO FS as a Gold Sponsor. Join us as we lead the conversation on data-driven transformation in financial services and discuss AI, Data Monetization, DataOps, Data Protection, Cloud Migration, and more at this 3-day virtual summit from March 2-4, 2021. Hear our experts at CDAO FS Tavant leaders Dr. Atul Varshneya (VP of Artificial Intelligence) and Vaibhav Sharma (BankTech Practice Head) will be speaking on “Adjusting to the Neo-normal: Evolving the Art of Credit Decisioning with AI & ML” at CDAO FS. The session is scheduled at 03:15 pm, EST on March 3. The session will focus on – Automating information capture and flow for STP (straight-through processing) Multi-parametric assessment for more accurate risk prediction Opportunity to engage in customer’s journey and value for the institution Atul and Vaibhav bring over two decades of experience in AI and BankTech leadership, respectively. They will share deep insights about industry needs and solutions as the Financial Services industry goes through unprecedented churn and change. Why you should take the time to meet Tavant at CDAO FS The global population generates up to 2.5 quintillion bytes of data every day. This opens up a world of possibilities for visionary businesses to become truly data-centric in their decision-making. The Financial Services industry is no different. At Tavant, we believe that this data explosion opens up brand new opportunities for the industry to begin the process of AI and ML adoption. Technological advances have led to more mature AI tools, and there is an increased awareness of AI applications in the industry. Needless to say, the ability to constantly learn and adapt to changing circumstances is what separates AI from other technologies. At CDAO FS, we are taking it up a notch. We look forward to sharing our latest innovations in AI ML applications in the new normal and how Tavant can enable you to navigate your business to the digital next. We look forward to seeing you there! For more information or to register for the event, click here.
Managing Product Recalls – Harness the power of Data
Product Recall – a word that could send chills down the spine for some manufacturers, spark media attention, hamper hard-earned reputation, and, no doubt, pose an unwanted financial burden. Despite stringent rules and regulations around product safety, recalls regularly make headlines. While no executive wants to face a recall, how it is handled determines the actual impact on the business. If an organization appropriately reacts and adjusts its operations, it can minimize damages and enhance its brand’s reputation for transparency, honesty, and genuine customer focus. Even after the need for a recall has been identified, the costs can quickly increase according to several associated factors list below: Identification The seriousness of the recall needs to be established; for example, is it contained to a consignment or batch, or a larger issue? If the product batch is at a warehouse waiting to be shipped, the recall cost will be far less than if the product is already in the consumer’s hand. Speed is of the essence at this point because if the product continues along the supply chain, the issue and cost can accelerate. Perception The emotional component of a recall can also wreak havoc on costs. For example, China’s parents are still haunted by an incident in 2008, the melamine baby milk scandal, and killed six infants. Many parents lost their trust in domestic brands, paving the way for foreign companies. Regulatory reporting Certain jurisdictions mandate reporting a product-related issue if any defects become known to a manufacturer or distributor, which may necessitate a recall. Companies need to decide which media channels should be used to release the recall notice. Social media platforms have reduced the potential costs, but advertising space in newspapers, television, and radio may still be required, and costs can increase considerably. The message about the recall will need to be carefully crafted to ensure it is clear and concise while also informing consumers that the company manages the issue effectively. Logistics The product may need to be physically removed from outlets, supermarkets, and/or showrooms. Retailers/dealers may also need to be reimbursed for their costs and loss of trade and remove the affected product from their shops/showrooms. The ripple effect If a faulty product is used as a component in other products, then the recall cost will also be considerably higher. While this is most common in the automotive sector, where a faulty part can easily damage other products in proximity, which must also be paid for, other sectors see similar situations. Business interruption Depending on the severity of the recall, lawyers, consultants, and extra staff may be required to help manage the recall. Also, the potentially lost person-hours associated with a recall’s distraction could be significant. Rehabilitation While the actual product recall is likely to be incredibly costly for a client, the expense does not stop once everything is safely off the shelves. The next significant cost can be returning the company and brand to its position before the recall, which may include extra promotional expense and sales promotion offers. Prevention is Key – what more can we do? AI and Machine Learning to the rescue! Big Data and emerging technologies underpin a positive response to an adverse event. Data analytics and emerging technologies in the supply chain, combined with customer intelligence and product knowledge, can help companies of all sizes more nimbly mitigate the detrimental effect of recall situations while simultaneously addressing customer concerns and preventing future recalls. We are in the era of industry 4.0, where smart and connected devices, powered by machine learning and AI, can predict faults and anomalies in the manufacturing process. Another way AI and machine learning can help the manufacturers is by analyzing the flood of manufacturing data received by machines. By analyzing this data thoroughly and looking for anomalies via machine learning, you can predict catastrophic failures earlier, avoiding total breakdown and saving businesses large amounts of revenue and brand equity. This, in turn, minimizes businesses’ need to issue recalls routinely or for consumers to suffer the potentially dangerous fallout from faulty equipment. Imagine being able to predict something before it does, pre-empt failures, and proactively take corrective actions. This is where artificial intelligence and machine learning come into play. The ability to create a full digital copy of an engine is achieved by creating ‘Digital Twins’, granular virtual copies of parts in the manufacturing process, which are enabled by deep learning and artificial intelligence. By creating ‘Digital Twins’, insights can be garnered to address the tiniest of issues that would otherwise be missed during a manual inspection process. When it comes to safety issues, the sooner they are discovered, the better. The advanced data analysis can help identify the early warning signs. Using multiple databases, complaints & reviews can be tracked and researched to pinpoint patterns with specific parts and performance. By investigating potential safety concerns and developing campaigns earlier, manufacturers can perform outreach to equipment owners more effectively to protect both the public and their brands. Text analytics platforms can empower big manufacturing companies to quickly assess their customers’ expectations, possible miscommunication issues, and the impact of the company’s actions on customer sentiment. This approach to crisis management enables businesses to seamlessly align internally and place their customers at the center of their product recall strategy. By combining machine learning and natural language processing, an organization can begin laying the foundation for cognitive analytics or artificial intelligence—sophisticated ways to make faster and more accurate decisions down the road. In the study, published in the Journal of the American Medical Informatics Association (JAMIA) Open, the researchers taught an existing “deep-learning” AI called Bidirectional Encoder Representation from Transformations (BERT) to predict food product recalls from Amazon reviews with about 74% accuracy. The AI also identified 20,000 reviews that suggested potentially unsafe food products that had not been investigated. Conclusion Putting strong measures to handle and counter the reasons that caused product recalls can help keep potential adversaries at bay. It fosters the goodwill needed to maintain
Predicting Quality Assurance Code for Warranty Claims using AI
The Warranty claim process for equipment manufacturers requires their dealers to provide certain details about the machine part e.g. part number, date of manufacture, etc. Some of the key details provided by the dealers are the descriptions of the problems seen by the dealer, the potential root cause of the problem, and the possible solution. These descriptions map to certain codes as prescribed by the manufacturer and the dealer must pick the right codes and submit the claim for warranty. The list of these codes is usually long, running into many hundreds of codes, and many times, dealers end up entering the wrong code or select a default code like ‘Others’ or ‘Miscellaneous’. Once the claim reaches the manufacturer, their subject matter experts (SMEs) must validate the codes as part of the Quality Assurance process and end up spending a lot of time in correcting the erroneous entries made by the dealers. This results in a longer claim cycle and cost for the manufacturer. Bringing AI into Quality Assurance One of Tavant’s customers has been facing this challenge and was exploring the options to solve this using Artificial Intelligence (AI). So, the idea was to use AI to predict the right code based on the description entered by the dealer in real-time so that the data entered is correct and the SMEs don’t have to spend a lot of time in validating and fixing the codes resulting in better data quality and significant savings for them. The Challenge At first glance, it looks like the problem can be solved as a classification problem using machine learning. However, there were certain challenges to handle such as: Unreliable historical data – as mentioned above, the available claims data in the warranty system has a large proportion of incorrect codes, hence cannot be relied upon as training data. For instance, we found that there was a lot of imbalance in the data with a lot of data under the ‘Miscellaneous’ category code Descriptions entered by the dealers are free-form text and can vary in the style of language used The customer QA team recently formulated a set of new codes making the current codes in the data obsolete The Solution Natural Language Processing (NLP) has progressed leaps and bounds with state of the art changing every few months. This has mainly been driven by the rise of Deep Learning and specifically the usage of Word Embeddings – starting with Word2Vec to the current state of the art models like BERT, ELMO, etc. In word embeddings, words having the same meaning have similar representation and can also maintain the context in which the word is used, thus being able to differentiate between things like Apple, the company, and Apple, the fruit. We also approached the problem using Word Embeddings. However, to handle the mentioned challenges and to build a production-grade solution, a lot more was required. Below are some of the salient features of our solution: Data augmentation – there was very little data (~ 2 descriptions/code) provided by the experts from the customer – recall they had formulated a set of brand-new codes. We used NLP based data augmentation techniques to generate realistic descriptions Semantic similarity – we used word embeddings to find semantically similar descriptions and associated codes Continual Learning – the solution presents the dealers with top-3 predictions, and the dealer can select the right one from them. This allows the model to learn and evolve with more data Low latency – the models predict the code with sub-second latency this ensuring good user experience High scalability – the models are containerized using Docker and orchestrated using Azure Kubernetes Services (AKS), ensuring high scalability with an increase in workload The whole exercise would have been meaningless without reasonably high accuracy. We beat the expectations and achieved accuracy levels of almost 90%. This will improve further as more data comes into the system. The Benefits The ROI of the solution is significant with respect to the improvements in business metrics, as mentioned below: Reduction in time for the dealers to select the QA codes Better data quality as dealers can no longer assign a “default” code for the descriptions entered Reduction in time spent by the manufacturer SMEs in correcting the codes entered by dealers – from weeks to minutes Reduced claim processing time
Bringing the Power of Artificial Intelligence to the Media Industry
In the coming years, Artificial Intelligence (AI) and Machine learning (ML) are going to change lives so much that today’s science-fiction will be tomorrow’s reality. Earlier, humans made machines to reduce physical efforts required to do jobs. AI and ML are now giving brains to these machines and making them smart, which further reduces efforts. AI and ML have a significant impact on every industry. Automated transportation, predictive policing, intelligent gaming, enhanced health care, and smart homes are a few examples. Like other domains, digital Media and Entertainment industry has evolved in leaps and bounds with Artificial Intelligence and Machine learning. With the power of Artificial Intelligence, the media industry is becoming more interactive, personalized, and engaged. The technology has enabled media providers to personalize entertainment to unimaginable levels using streaming services, including on-demand movies, music, live telecasts, etc. These technologies provide many algorithms to eliminate buffering and low-quality playback, getting you the best quality content using intelligence from your ISP providers. Also, with concepts of data science, ML algorithms intelligently analyze unlimited streaming data to understand consumer’s viewing habits to offer more useful recommendations. Along with this, the sequence-to-sequence learning technique of Machine learning can translate your content from one language to another, from one writing style to another, allowing your content to reach distinct audiences more efficiently. Similarly, NLP (Natural Language Processing) algorithms help writing top trending news stories to decrease the time to produce new content. Shelley, an AI tool developed by MIT, allows users to write horror and fictional stories through deep learning algorithms. Following this trend, one could state that the creators of the next great content may not be human at all. Traditional media planning models have limited information on behaviors and purchasing patterns of the targeted audience. AI and ML can power numerous kinds of models, such as: Machine Learning-based pay-per-click campaigns Machine Learning-based content campaigns Machine Learning-based hyper-targeted email campaigns Efficient predictive data modeling and planning These ML models help media planners and marketers increase customer reach, improve the relevance of the audience, and create a great user experience. With extensive interactions and existing research, AI will soon influence market strategies, including business models and sales processes. In the future, Sales and Media planners will be assisted by AI agents who will monitor telephonic conversations in real-time. For example, such AI agents might infer from the client’s tone that the client is unhappy with the approach of that media planner or salesperson, and AI agents might help them decide the best possible strategy. In this way, AI could augment the capabilities of team members. With the endless possibilities offered by AI, we certainly have exciting times ahead.
3 Reasons You Must Adopt AI-Based Quality Engineering
Regulations are constantly changing in the mortgage industry. Lenders are under continuous pressure to meet fast approaching deadlines on UCD and HMDA. The Uniform Closing Dataset (UCD) is a standard industry dataset enabling information on the CFPB’s Closing Disclosure to be communicated electronically. The first deadline of 25 September 2017 mandates lenders to deliver borrower data and Closing Disclosure in the UCD file. UCD improves loan quality through increased data accuracy and consistency. This is of interest to the GSEs as it enhances the loan’s eligibility for sale in secondary markets. The year 2018 brings updates to the HMDA. The new HMDA rule requires over 48 data points to be collected, recorded and reported. This includes multiple new data points and a few modified from the previous rule. New fields include credit scores, CLTV ratio, DTI ratio, detailed demographic data etc. The CFPB asserts that the changes improve the quality and type of data reported by financial institutions leading to greater transparency. The updated regulations bring a new set of challenges to lenders. Investments in technology systems and processes can potentially increase the ever-rising loan origination cost. Data privacy and security is another concern. With the increased number of data fields, protecting sensitive borrower information is a priority. Additional data can also be used in fair lending claims thereby increasing litigations risks and costs. Since 2008, the mortgage industry has been taking giant strides in improving data reporting and compliance standards. TRID rule impacted the industry at almost every point along the transaction, and UCD/ HMDA will change the way data is collected, recorded, reported and delivered. Over the years, Tavant’s mortgage expertise has helped lenders implement regulatory changes with cutting edge technologies. In 2015, we helped multiple lenders achieve TRID compliance ahead of schedule. In 2017, we are doing the same with HMDA and UCD. It’s time to achieve Accelerated Compliance with Tavant Testing. The countdown is on! To learn more about our testing solution please visit: UCD/HMDA Compliance Testing by Tavant
Blockchain – An Emerging Trend in Warranty Management
Warranty providers today are still dealing with the three critical challenges of the industry: protecting against fraudulent claims, detecting counterfeit products, and deciding on the status of coverage. Businesses are becoming increasingly complex with more vendors, dispersed manufacturing facilities, new distribution channels, and disruptive business models to make matters worse. It’s small wonder then that the processing and administration costs of warranty keep on rising. A study[1] by IBM found that in the electronics industry, only one-third of the warranty costs go towards repair or replacement of defective goods, with two-thirds being spent on processing and administration. There is a dire need to find better ways of managing warranties to keep costs from rising steadily. Technology has always provided us with solutions to address these problems in the past, so will it come to the rescue again? Well, it looks like a solution may already be around the corner, based on an emerging technology called blockchain, which originally evolved to enable decentralized transactional data sharing across large networks of untrusted participants, and is based on the concept of a distributed public ledger. Such a distributed ledger technology (DLT) could also be used to track-and-trace parts throughout the supply chain with a complete history of events related to the part. This capability would help in addressing all the three key warranty challenges mentioned above. Since the blockchain-based public ledger is accessible everywhere, warranty providers would be able to validate the claim and the warranty status at any point in the warranty management process in order to make quick decisions. Also, using the track-and-trace capability of the ledger, they could readily trace the manufacturer of the item, helping them get the repair or replacement process started immediately. The extensive history of the part available would also make decisions on claims easy for the manufacturer. Once the complete lifecycle of a part is available through a trusted public ledger, it would be possible to see the exact time and place of manufacture, note when the part transited through the warehouses of the distributor or supplier, check when it showed-up in the seller’s inventory, and find out when and to whom it was finally sold. This detailed traceability would make it very easy to detect counterfeits, which would fail to show the expected transition history through the supply chain of authorized manufacturers, distributors, and sellers. Thus, blockchain-based systems would make the whole warranty management workflow much faster, simpler, and fraud-resistant, drastically reducing administrative and processing costs. A welcome side-effect of a transparent, fast, and efficient claim-handling process would be enhanced customer experience. Thus, blockchain technology could ultimately have a direct bearing on customer satisfaction and brand health while cutting down costs and improving the provider’s bottom-line. Don’t get too excited yet, though; this technology is still at the proof-of-concept stage in most industries with very few production deployments. However, the applicability of the technology to warranty management is pretty certain. It is just a matter of time before solutions using blockchain get proven, and as we have already discussed above, they will not only address the issues of fraudulent claims, counterfeit parts, and unclear warranty status, but will also increase customer satisfaction and reduce costs by making the claim-handling process fast, fair, and fail-safe. Therefore, if you are a warranty provider, get ready as a blockchain-based innovation is coming soon to a warranty solution near you. Want to Explore More? To gain valuable insights into how the latest innovations can help you stay ahead of the market, register for our webinar with a guest speaker from IDC, on September 10, where we discuss the latest innovations transforming warranty management. [1]IBM: Powering warranty reinvention (https://www.ibm.com/downloads/cas/D6QBER28)
Empower your Aftermarket Business with Intelligent Decisions
The Changing Aftermarket Industry According to a global strategic business [i]report, the global automotive aftermarket industry is expected to reach $722.8 billion by 2020. This rising demand for aftermarket parts and services is driving new growth and revenue opportunities for automotive aftermarket organizations. Moreover, digital transformation is re-imagining the automotive industry. Platform-based innovation and hyper-connectivity are shaping the new world of the automobile. Interestingly, aftermarket, the secondary market of the automotive industry is also experiencing this paradigm shift from traditional legacy systems to the digitalized world powered by AI, Machine Learning, IoT, Big Data, Analytics and Mobility. Rising Customer Expectations There is a significant change in the customer buying behavior which has acted as a catalyst in the progress of automotive aftermarket. Interestingly, today’s consumers are keeping their vehicles longer and are more aware of the importance of preventive maintenance and scheduled servicing to maximize the lifetime value of their vehicles. Furthermore, in today’s modern parts marketplace, the millennial customers have become more sophisticated and mobile-oriented while staying connected with their local automobile retailer. They are more in control of the buying process than ever before – with the ability to price, source, and obtain products and parts from a wide variety of sources, including spurious parts suppliers who don’t have the same overheads as the OEM. Needless to say, the consumers are now expecting a seamless experience spanning via omnichannel including physical retail supply shops, apps, websites and so on. Data, Data Everywhere The exponential growth of connectivity and data in manufacturing is drifting aftermarket services towards a new era. The next generation of tools and processes is equipped with next-gen technologies that enable unprecedented collection and transmission of data, which can be exploited to improve aftermarket operations. However, the aftermarket value chain is still highly segmented in disparate data silos. Each player focuses on its perimeter, where it exercises a strategic control thanks to its assets (parts IP, integrated offering, global network, and so on). Business models are still primitive and rely on service contracts (diagnosis, repair, parts, and maintenance) using a transactional mode (cost per operation). Artificial Intelligence & Machine Learning to Rescue Leveraging IoT technologies and platforms built into devices have increased the potential for new revenue streams through innovative data sharing/insight opportunities. And the good news is the large volumes of data generated by IoT devices can now be understood, acted upon and monetized with the help of AI and ML. Organizations can consider integrating IoT data with the existing warranty data to obtain new insights into their customers, products, and operations. In turn, this can lead to optimized product service, enhanced support processes, and the provision of new and differentiating customer experiences, all of which can help in driving revenue. Eventually, improved warranty performance has a direct impact on the customer experience; for example, if a consumer feels that a company acknowledges when products fail to meet up with their expectations, they are more likely to stay in the future, building brand loyalty. The time to act is Now If you are looking to implement a world-class warranty solution without investing heavily in infrastructure or the resources required to deploy & maintain the solution at your premises; our on-demand solution is tailor-made for you. By applying AI and machine learning algorithms to massive amounts of customer data, Tavant’s enterprise warranty solution TWOD on the Salesforce Cloud combines its warranty solution expertise with industry best practices to offer end-to-end warranty lifecycle management. It provides enhanced visibility and proactively populates business opportunities for the sales, service, and marketing teams in their CRM. Want to Explore More? To delve deeper, attend our engaging session on ‘Artificial Intelligence, Machine Learning and the world of making smarter, faster and better decisions’ at WCM 19 and learn how to unlock your sales and revenue potential or just say [email protected] to schedule a meeting.