Case studies Archives - Arrk Group

AI Powered Web Development

Sandeep Parkhande — Fri, 10 May 2024 13:18:59 +0000

AI-Powered Solution Transforms Web Development and Cost Efficiency in Business Intelligence

We pride ourselves on delivering progressive solutions that encourage our client’s businesses. Recently, we collaborated with a client in the Business Intelligence sector to address their challenges and transform their development process. Here’s how we achieved remarkable results.

Customer

Our client, operating in the Business Intelligence sector, sought to create a web-based application to enhance data analysis and reporting capabilities. Unlike others, our client prioritizes data discovery, enabling businesses to focus on critical aspects. With support from our client, businesses can achieve next-level data navigation that is focused on market insights and business intelligence, which will help build a more innovative and competitive brand.

Data-focused application

Market insights

Business intelligence

Problem Statement

Our client faced significant difficulties when it came to meeting their client deadlines. This led to an escalation in costs that created a bad reputation in the market. The challenge our client faced was the use of traditional development methods that lacked the agility and efficiency that is required to complete a project on time. By recognizing this problem, our client saw the need to develop a web-based application that would help speed up their development process without reducing the quality assured.

Missed client deadlines

Reputation damage

Cost escalation

Need for agile development

Solution Development

At Arrk Group, we helped spearhead a pioneering initiative to empower our clients with cutting-edge AI-based productivity tools such as ChatGPT and Cody to help streamline their overall development process. Leveraging these tools, we seamlessly integrated React UI for the front end and Python for the back end, optimizing the developmental stack to improve performance and scalability. With our approach of harnessing AI-generated codes throughout the entire application lifecycle, we ensured that rapid iteration of the cycle occurred and sped up the overall delivery timeline without compromising functionality or quality.

Pioneering AI initiative

Streamlined development process

React UI and Python integration

Rapid iteration and delivery

Outcomes

We successfully utilized AI-enabled tools to help improve our client’s overall data extraction, analysis, and development processes. By combining the ingenuity of our team members with the latest AI tools available in the market, we helped our client reach the following outcomes:

75% Reduction in Development Time and Costs:
By harnessing AI tools, we were able to implement the project in one week rather than the estimated four weeks quoted without using AI. This reduction in development time led to a 75% decrease in overall effort and cost for the client, which in turn enabled them to allocate their resources effectively.
Improved overall efficiency and productivity:
AI-driven development helped accelerate the delivery process for the web-based application and also optimized the resources allocated. This allowed the client to focus more on their core business activities and strategic initiatives rather than process management.
Uncompromised Quality:
Even though the entire development process saw an acceleration in the timeline, the quality of the application remained uncompromised. This was due to rigorous testing and validation processes implemented by our team. In the end, our client received a fully functioning solution that not only met their needs but also exceeded their expectations.
Competitive Advantage:
As the web-based application was deployed within one week rather than four, the client gained an overall competitive edge by adapting to the change in the market and seizing opportunities before their competitors.

In summary, our integration of AI productivity tools not only addressed our client’s immediate needs but also crafted the way for future success in the dynamic Business Intelligence industry. Trust Arrk Group to revolutionize your development process and drive efficiency.

Reduction in Development Time and Cost

Improved Efficiency and Productivity

Uncompromised Quality

Competitive Advantage

More of Our Case Studies

See all case studies

The post AI Powered Web Development appeared first on Arrk Group.

AI-driven software rewrite

Sandeep Parkhande — Fri, 10 May 2024 13:17:34 +0000

Implementation of an AI-driven software rewrite for a .NET application to execute the full potential of cloud and mobile technologies

Customer

Our client, a prominent player in the healthcare industry, has stood as a beacon of providing quality care to millions. This globally recognized institution strives to innovate and adapt to the ever-evolving landscape of the healthcare sector. The client realized the critical need for a web-based application that would improve overall patient care and optimize the efficiency of their operations.

Web-based application

Focus on innovation

Improved patient care

Problem Statement

Our client was faced with stringent timelines and constraints on resources as they struggled to develop a comprehensive web-based application by using conventional development methods. The emergent need to deploy a robust solution is what prompted the need to explore innovative approaches to help speed up the development process without reducing the quality.

Stringent timelines

Resource constraints

Conventional development methods

LLM and ChatGPT

Solution Development

We at Arrk Group embarked on a journey to help our healthcare clients by using AI-driven productivity tools. By leveraging these cutting-edge AI tools, such as ChatGPT, we helped not only innovate the development process but speed it up as well. Our team of experts meticulously designed UI interfaces using React UI, while the backend structure was developed using .Net and MS SQL Server. By using AI-generated codes throughout the application, we were able to reduce the development lifecycle from 2 weeks to only three days. This also led to savings of upto 80% in both costs and efficiency for our customers.

AI-driven productivity tools

Innovative and accelerated development

Reduced timeline

Cost Saving

Outcomes

With the time constraint and the limited resources our client faced, we at Arrk Group were able to consistently deliver a web-based application that not only met their standards of quality but also innovation. This was only possible by implementing AI-driven tools such as ChatGPT, which helped speed up the entire workflow. The outcomes of this project were:

Rapid deployment:
With the strategic use of AI tools, we were able to complete the entire web-based application in just three days – a highly remarkable achievement, considering that our earlier estimate was two weeks. This speedy delivery helped our healthcare client address their critical needs of overall patient care while offering a competitive edge over their competitors.
High customer satisfaction:
Our client highly appreciated the expedited delivery of the application, and they applauded us for surpassing their expectations. The rapid turnaround of only three days not only demonstrated our commitment to excellence but also reinforced our reputation as a trusted technology partner in the healthcare industry to our client.
Savings in cost and effort:
By using AI-driven tools, we were able to reduce our client’s costs and effort by 80%. This efficiency helped our client allocate more resources towards patient care and improve business value.
Continuous optimization: With our commitment to adapting innovative development processes, we ensure that the solutions we offer remain at the forefront of technological innovation that is delivered to our customers.

Our innovative approach of utilizing AI-driven tools to develop a web-based application for our client exemplifies our commitment to not only achieve sustainable growth in a limited period but also improve overall patient outcomes in the healthcare industry.

Rapid deployment

High customer satisfaction

Continuous optimization

Cost Reduction

More of Our Case Studies

See all case studies

The post AI-driven software rewrite appeared first on Arrk Group.

AI Recommender System to Boost Engagement & Revenue

Sandeep Parkhande — Fri, 10 May 2024 13:11:56 +0000

Implementation of AI-powered recommender systems for enhanced customer engagement and overall Revenue Growth.

The API endpoint was created to integrate the web and mobile apps and capture relevant data, leading to a 30% increase in the first three months.

Customer

A diverse range of customers from multiple industries sought to enhance their overall online presence by driving revenue growth through personalized offer recommendations across their websites and apps.

Diverse customer base

Revenue growth focus

Personalized offers

Problem Statement

Traditional recommendation systems often fell short in delivering personalized experiences tailored to individual user preferences. Recognizing the importance of relevance in driving customer engagement and overall conversion rates, businesses sought innovative solutions to implement overall intelligent AI-based recommenders.

Limitations of traditional systems

Importance of relevance

Shift towards AI-based solutions

LLM and ChatGPT

Solution Development

We at Arrk Group embarked on a collaborative journey with clients to help understand their unique requirements and help capture relevant data points that are essential for personalized recommendations. By leveraging AWS personalize, a management recommendation system in the Amazon Web Services ecosystem, our team added a sophisticated algorithm to analyze user interaction history and help us identify any patterns that indicate the overall user preference and behavior. We then trained the model using historical interaction data that helped generate personalized recommendations that were tailor-made to every user’s unique preference.

Collaborative client journey

AWS Personalize implementation

User interaction analysis

Tailor-made recommendations

Outcomes

We at Arrk Group found that most of our clients wanted to help drive growth through personalized messaging to their customers via their website and apps. With our AWS management recommendation system, our clients saw the following outcomes:

Improved personalized offers:
By harnessing the power of AI and AWs management Personalize, our clients saw a significant rise in the relevance of offers presented to their customers. This personalization helped improve engagement rates and customer satisfaction and drive growth.
Impact on revenue:
By implementing an intelligent recommender system, our clients saw a 30% increase in offer-based revenue within the first three months. This tangible impact highlighted the effectiveness of personalization in generating revenue and improving conversions.
Continued improvement:
We at Arrk Group are always looking towards continuous refinement and optimization of the workflow. By fine-tuning ongoing processes, we help deliver more relevant recommendations that improve our customers’ engagement rates and revenue generation.
Integration of API: We created an API endpoint to help integrate the personalized AWS engine into our clients’ websites and applications. This helped our clients by providing real-time relevant offers to users, improving browsing experiences, and driving conversion rates.

We at Arrk Group strive to help our customers with the latest innovative approaches to improve business. With our AI-powered recommender system, we help our clients resonate with their audiences by providing personalized experiences that foster long-term loyalty and overall revenue growth

Improved personalized offers

30% increase in offer-based revenue

API Integration

More of Our Case Studies

See all case studies

The post AI Recommender System to Boost Engagement & Revenue appeared first on Arrk Group.

Cost Effective Marketing Tool Implementation

Sandeep Parkhande — Fri, 15 Mar 2024 08:52:14 +0000

Arrk's integration with OneSignal empowered our client with dynamic list creation, detailed engagement feedback, and rapid, cost-effective communication capabilities, leading to a 50% reduction in customer communication costs and streamlined promotional activities.

Customer

OneVoice operates a UK-wide closed-community performance-marketing platform connecting youth-orientated communities with national and international brands. They provide membership options for unions, associations and professional bodies. The platform connects 1M+ members (end users) with brands offering discounts and other promotions on a wide range of products.

As a UK-based digital marketing company with limited in-house tech skills, OneVoice has been working with Arrk since 2017 to help power their tech and data solutions.

1M+ Members

Discounts and Promotions

Partnership Since 2017

Problem Statement

The Customer was struggling to send notifications to different user segments. This included sending in-app/push notifications and web notifications to users who might be interested in specific brands/offers. In order to increase revenue a need arose for sending personalised notifications to less engaged users. Due to this, the requirement to send push notifications to end users on mobile and the web came to the forefront.

However, creating a communication platform to send out notifications via the web and mobile was a time-consuming and expensive affair. Also, for mobile users, the platform would need to offer separate solutions for both iOS and Android users.

So, to remove these challenges, Arrk recommended the implementation of a one-stop communication platform that would send out emails, in-app/web messages and SMS notifications to users at a minimal cost. The platform that Arrk suggested was OneSignal.

Arrk designed, developed, and implemented an integration between our client’s core systems and OneSignal to improve their notification game without incurring significant costs.

Notification Issues

Expensive Affair

Time Consuming

LLM and ChatGPT

Solution Development

In a strategic move to improve analytics, Arrk proposed OneSignal as the best communications platform for OneVoice. By collaborating closely with the SAAS platform, Arrk deepened its understanding of its integration methods and APIs. This resulted in a seamless integration of back-end systems with OneSignal that empowered the client with easy customer communications. However, this did not stop there; Arrk took charge of crafting the dynamic templates for push notifications and in-app messages in the OneSignal platform itself to ensure a unified user experience.

The final touch of using the tool was a smooth migration of data from our client to OneSignal to make an efficient transition.

After a detailed analysis, Arrk recommended OneVoice use OneSignal as the communications platform
Arrk worked with SAAS vendor OneSignal to understand their integration methods and APIs.
For all customer interaction, the back-end system was integrated with OneSignal to send out all communications
All templates for creating push and in-app notifications were created in OneSignal
Data migration from OneVoice to OneSignal was done seamlessly

Improved Analytics

Seamless Integration

Dynamic Templates

Data Migration

Outcomes

Our client now has the ability to create multiple lists in OneSignal, which they can reach out to such users as engaged posts/less engaged posts/new users, and similar.
Feedback on customer engagement such as email opened, clicks, app messages opened etc.
Ability to send out emails to millions of users in a few minutes.
Ability to generate instant in-app/In-web messages and campaigns for promotional activities with minimal clicks and configuration.
The system integration resulted in a reduction in costs related to customer communications by 50% as compared to any similar ad hoc implementation.

Customer Feedback

Email Communication

Instant Messages

Cost Reduction

More of Our Case Studies

See all case studies

The post Cost Effective Marketing Tool Implementation appeared first on Arrk Group.

Revolutionizing Construction Data Management

Drashya Kuruwa — Fri, 15 Mar 2024 04:33:25 +0000

Arrk Engineered a two-tier process to harvest bulk data extraction from PDFs - resulting in the reduction of costs incurred by the client while improving the efficiency of the process.

Customer

Our client is an award-winning eLearning company that offers corporate training solutions to help improve workforce performance while driving business on a global level. With over 25+ years of experience in building meaningful learning solutions, the brand has helped transform people into leaders of tomorrow with a 360-degree approach to training, leadership, procurement, and consulting.

Award Winning Company

Corporate Training Solutions

360 Degree Approach

Problem Statement

Our client was faced with multiple challenges in their quest to gather tabular data from PDF files that contained numerous financial details. One of the biggest problems was to extract information accurately for multiple channels within a single file. This meant that to avoid any discrepancies in the extraction of data, a sophisticated extraction tool needed to be used. The current in-house tool uses Python, Tesseract, Spacy, and Transformer to gather bulk data from PDFs.

Another issue that our client faced is that while the in-house PDF system is robust, it cannot extract tabular data from certain PDFs. This incomplete data extraction hinders the ability to not only gather insights but also impact the entire decision-making process. Our client wanted a solution to balance the cost-effectiveness while ensuring that the data extracted was accurate. However, a cost-intensive solution for every single PDF file did not seem practical. So, to strike the right balance between cost and efficiency was the need of the hour.

Information Extraction

Robust System

Data Efficiency

LLM and ChatGPT

Solution Development

To address the challenges, we at Arrk designed a two-tiered solution that combined the in-house tool with AI-driven technology.

For the in-house PDF crawling system, we implemented an algorithm that is capable of handling multiple financial instruments and tables within a single PDF file. The system was made to crawl the PDFs periodically to extract the data and prioritize accuracy above all else. By using the in-house solution, we allowed our client to achieve bulk extraction of data without any additional costs.

To act as a safe gate where the in-house solution did not work, the PDF was automatically routed to the AIMLbased Amazon Textract solution. The tool is driven by advanced machine learning to work as a fail-safe mechanism where all tabular data can be extracted accurately from PDFs. But, this platform would only be used when the in-house tool failed. Optimizing the use of Amazon Textract meant that the client’s expenses were minimized and were now cost-effective.

AI Driven Tool

Bulk Data Extraction

Cost Effective

Outcomes

Collaborative results with our client helped yield the following results:

Combining the use of the in-house crawling system and Amazon Textract ensured that the most relevant data was extracted from the PDF.
Prioritizing the in-house tool resulted in significant savings as the AI tool was only used for challenging situations.
The two-tiered approach led to an overall efficient bulk data extraction process and maintained the balance between cost and performance.

Seamless Collaboration

Optimal Prioritization

Two Tiered Approach

More of Our Case Studies

See all case studies

The post Revolutionizing Construction Data Management appeared first on Arrk Group.

Enhancing Web Scraping Capacity Using Amazon Sagemaker and AWS Cloud Services

Drashya Kuruwa — Thu, 14 Mar 2024 11:50:52 +0000

Arrk helped improve the growth efficiency by 25% and improve productivity by 50% with the implementation of the double tag team of Amazon Sagemaker and AWS Cloud Services to facilitate challenges faced in the data management process

Customer

Our client is one of the leading players in the construction data businesses, specializing in offering comprehensive solutions to professionals in the construction industry. They are headquartered in Cheshire, UK, and offer focused data-driven insights to help shape the construction industry landscape.

We have been partners with our client since 2005 to help mark the beginning of collaborative efforts to improve their data management facilities.

Construction Data Business

Partners Since 2005

Partnership Since 2017

Problem Statement

Our client was faced with multiple challenges in the data management process that required a complete overhaul of their tools. The existing web scraping system needed the manual setup of machines, which was not only time-consuming but also needed high levels of manpower. This meant that the development cycle was hampered, and there was loss of data.

Because of the machinery used, it meant that only one developer could work on one machine at a time. This not only hampered the collaborative efforts between teams but also impeded parallel development processes.

Also, the costs associated with the total setup and maintenance of the machines for developers were fairly high, which led to financial problems. In fact, our client found it difficult to allocate resources away from these machines, which in turn caused a suboptimal balance between the operational aspect and cost
efficiency.

Data Loss

Robust System

Hindered Team collaboration

LLM and ChatGPT

Solution Development

We at Arrk took a look at the problems our client was facing and tailor-made a solution leveraging two tools – Amazon Sagemaker and AWS Cloud Services. As per our initial assessment, we introduced Amazon Sagemaker into the machine setup process. This reduced the configuration time, especially with GPUs, and better extraction of data.

We then collaborated with Sagemaker and AWS Cloud Services to ensure that multiple developers could work on diverse projects at the same time. This started fostering an environment of innovative and collaborative efforts to improve the efficiency and speed of the development team as a whole.

Finally, by integrating the AWS Cloud Service, we brought in scalable infrastructure that made our client adapt dynamic workloads for the developers. By doing this, the company achieved substantial savings and
could optimize its resource allocation without having to compromise on its productivity.

Sagemaker + AWS

Collaborative Efforts

Scalable Infrastructure

Resource Optimization

Outcomes

A substantial increase in efficiency by 25% led to the sorting and management of larger volumes of data.
Reduction in costs by 30% p.a., particularly in the machine setup and allocation of resources stages.
Various developers could collaborate and innovate within the team effortlessly.
Teams could now focus more on the business problem aspect rather than infrastructure-related tasks.
Workloads could now be managed effortlessly without compromising the performance of teams, and productivity improved by 50% without any added costs.

Cost Reduction

Managed Workload

Improved Productivity

Cost Reduction

More of Our Case Studies

See all case studies

The post Enhancing Web Scraping Capacity Using Amazon Sagemaker and AWS Cloud Services appeared first on Arrk Group.

Omni-Channel Marketing Tool Implementation

Drashya Kuruwa — Wed, 06 Dec 2023 07:10:00 +0000

How Arrk’s Implementation of Iterable enabled Client to save cross-channel marketing costs by 48% in 6 months Resulting in Increased digital marketing throughput and improved customer acquisition

Customer

Our Client operates a UK-wide closed-community performance-marketing platform connecting youth-orientated communities with national and international brands. They provide membership systems to unions, associations and professional bodies and connect 1M+ members (end users) with brands via discount offers and other promotions on a wide range of products.

As a UK-based digital marketing company with limited in-house tech skills, our client has been working with Arrk since 2017 to help power its tech and data solutions.

Problem Statement

Our Customer was using multiple systems and communication platforms to design, plan and execute cross-channel marketing campaigns, service updates and notifications to their 1M+ consumer end-users. This resulted in simultaneously storing the user’s data in several platforms and was time-consuming for the marketing and customer success teams as they had to juggle between the various systems resulting in a suboptimal omnichannel experience for the end-users.

The use of multiple independent platforms required the Customer to integrate and maintain data between various systems which aside from being time-consuming and costly. Also introduced risks of data breach plus many limitations in terms of the nature of the campaigns/comms that could be executed, the efficacy of the comms and the quality of the end-users experience.

To fix this Arrk recommends to the client that they implement an omnichannel marketing/CDP* platform, tightly integrated into their existing core systems and their data architecture. After a short selection process, Iterable (www.iterable.com) was selected and Arrk led a rapid, complex integration.

Arrk designed, developed and implemented an integration between their core systems/data warehouse and Iterable. It enabled our Customer to rapidly transition to the execution of high-volume end-user communication in near real-time coordinated and orchestrated over multiple digital channels including web, mobile, email and social media.

Data Warehouse & Iterable

High Volume End-User Communication

Multiple Communication Platforms

LLM and ChatGPT

Solution Development

With Arrk’s implementation of Iterable the Customer’s marketing and comms teams have a centralised cross-channel communication platform which enables richer personalisation and segmentation of end-users and communications to provide end-users the info they need via the right medium at the right time.

Arrk’s native integration with the Digioh forms/preference management platform also enriches the comms to help segment and deliver targeted comms at scale. Arrk’s use of Iterable’s Catalog feature pulls in live, customised content to individual comms which is a capability that was not available with the previous systems based as it was on a basket of disparate platform providers.

The project was initiated by Arrk with an EmbArrk™ discovery process which mapped out the as-is processes and data/comms journeys and designed the to-be for our Customer. We also explored and costed various platform options, fitting each to the need. Following this research, design and planning phase, we recommended the Iterable platform considering that it is a one-stop cross-channel comms and CDP platform, and it has various other features such as user segmentation and catalogues which we anticipated would greatly aid the Customers in planning and executing automated bulk-sends.

The feature delivered to our customer’s marketing and customer success teams included:

A one-stop solution for sending cross-channel comms to end users.
This resulted in improved productivity across all teams and a significant improvement in the efficacy and impact of marketing comms.
The flexibility to design and curate campaigns based on flexible end-user segmentation resulted in improved sales conversions and resultant revenue.
Easy and better ways to create email templates, push/in-app and web notifications.
User data and user events are captured in real-time for accurate reporting and end-user segmentation.
Multiple inbuilt journeys were created in Iterable to send automated campaigns at a large scale.
Easy integration with mobile app.

Requirement Collection

Structured Query Conversion

Data Repository Integration

Outcomes

Increased revenue
48% reduction in cost with Iterable compared to integrating with multiple platforms.
Thousands of human work hours are saved annually for the Customer’s customer success team.
Better end-user segmentation was created enabling more targeted comms, at a large scale (thousands of tightly targeted campaigns sent at a time).
Avoid the storing of user information on multiple platforms reducing the risk of data inaccuracy, customer complaints and data breaches.

Better End-user segmentation

Increased revenue

Reducing risk of data inaccuracy

More of Our Case Studies

See all case studies

The post Omni-Channel Marketing Tool Implementation appeared first on Arrk Group.

Natural Language Search Implementation for Customer Loyalty Program (ChatGPT)

Drashya Kuruwa — Fri, 20 Oct 2023 06:40:50 +0000

Natural Language Search Implementation for Customer Loyalty Program (ChatGPT)

Our client, a digital performance marketing business has amassed a wealth of valuable behavioural data based on user demographics and usage patterns. Although this data holds enormous potential for discovering new business opportunities, it remained buried inside a set of large data repositories, which were challenging to interrogate. This meant that the marketing and member engagement teams were unable to efficiently access this valuable business intelligence.

Customer

A market-leading digital business operating a nationwide membership scheme serving circa. 2 million members across the UK. In addition to an award-winning membership, events and voting platform, our customer also provides a suite of performance marketing services to national and international brands, all built around the central tenet of ‘community first’.

Problem Statement

The untapped potential in the behavioural data was well understood by our customers. However, they faced a significant challenge in accessing and decoding it. Traditional business intelligence tools like Power BI were considered but fell short of the customer’s need for a flexible, interactive and user-friendly method of integrating the data. Our customer sought to enable users to ask questions in plain, natural language and receive prompt, accurate and insightful responses. Our AI Engineering team designed and built a solution which converts user queries into often complex structured database queries and executes them against the data repositories to generate rapid results. LLM (Large Language Models), ChatGPT, and prompt engineering emerged as key enablers of this solution.

Data Potential Realization

User-Friendly Search Experience

LLM and ChatGPT

Natural Language Query

Solution Development

The project started with a workshop-based discovery phase, following which we conducted a short engineering-lab-based R&D / feasibility activity. Having established the boundaries and feasibility of the design concept, we executed a rapid, interactive development process. A team of eight AI/ML Engineers were assigned to build the PoC service. Further AI Engineering work is ongoing.

The project hinged on the innovative use of Large Language Models, specifically ChatGPT, to facilitate natural language search and query design. The following key components played a vital role:

Structured Query Conversion: User queries, expressed in plain natural language, were translated into structured queries that could interrogate the data repositories effectively.
Data Repository Integration: The structured queries were executed against the data repositories to quickly extract accurate results based on user intent.
Advanced Interpretation: using prompt engineering, the AI Engineering team created a context for ChatGPT which enabled it to achieve a high level of proficiency in accurately interpreting user queries. It could handle various query structures, including those with unstructured elements such as flexible date formats like “Next year,” “within 12 months from now,” “Q4 2023,” and more.

Requirement Collection

Structured Query Conversion

Data Repository Integration

Outcomes

The project has already delivered substantial value and generated tremendous enthusiasm within the customer’s organisation. Some notable achievements include:

Exceptional Interpretation: our AI Engineering team’s design enabled ChatGPT to interpret user questions in a manner which surpassed previous natural language processing efforts undertaken in earlier initiatives. It can decipher complex queries with ease, accommodating various formats and expressions.
User-Friendly Interaction: Users now enjoy a user-friendly, conversational interface that allows them to seek data insights in a frictionless manner by simply typing their queries in natural language.
Enormous Promise: The PoC, currently operating via a command line, demonstrates great promise, with the potential to revolutionise how its users interact with and extract insights from the ocean of behavioural data.

The client’s pursuit of an AI engineered solution, empowering users with a natural language search capability, represents a significant step towards unlocking the hidden potential of their valuable data. The combination of Large Language Models, ChatGPT, and prompt engineering has opened new horizons for data exploration and integration and has the potential to elevate its position in the market. As the project progresses, it is poised to render increasingly precise and commercially valuable intelligence, demonstrating the transformative power of AI Engineering and advanced language models in making data accessible and actionable.

Exceptional Interpretation

Data Exploration and Transformation

Accessible and Actionable Data

More of Our Case Studies

See all case studies

The post Natural Language Search Implementation for Customer Loyalty Program (ChatGPT) appeared first on Arrk Group.

Utilised an AI Chatbot to Decrease Customer Support Tickets by 89%

Drashya Kuruwa — Fri, 20 Oct 2023 06:08:04 +0000

Utilised an AI Chatbot to Decrease Customer Support Tickets by 89%

Our client’s customers previously accessed limited reports through the platform’s dashboard, requiring them to contact customer support for other metrics. This lack of customization resulted in delays and dissatisfaction. To fix this, they partnered with Arrk’s AI Engineering team to create an AI-enabled chatbot. The chatbot handles dynamic queries, quickly presenting complex statistics from the database, improving the customer experience and solving the previous issue of delayed replies and high turnaround times for human-generated tailored reports.

Customer

This client is a services-based company, providing outsourced support in various sectors including Telecom, Automotive, Insurance, Finance, Banking, Accounting, HR, and Recruitment. Our Client is one of the top companies with a client base of 5000+ companies across multiple countries and continues to grow at an exceptional rate.

Problem Statement

Using the platform’s inbuilt dashboard, their customers could access reports related to various back-office processes.

However, these reports had limitations, often forcing customers to contact the client’s customer support team for insights and data beyond these reports. Customers couldn’t drill down custom reports easily, leading to repeated contact with customer support for other details.

Ultimately, clients had to either email tailored report requests to the support team, create service desk tickets, or endure long phone queues until a customer service representative assisted them.

This often resulted in late initial responses and extended turnaround times for getting tailored reports, eventually leading to a diminished customer experience and client attrition.

Recognizing the need for an expandable solution, they partnered with Arrk to build an AI enabled based chatbot able to handle dynamic queries and supply timely, contextually appropriate information from the database.

Custom Reports

Extended Turnaround Times

AI-based Chatbot

Solution Development

We started with a two-week, intensive EmbArrk™ project discovery workshop to gather and elaborate requirements and specifications and to establish consensus among all stakeholders.

After careful consideration, we decided to have three separate Scrum teams, one for each business component.

Arrk’s AI Engineering team selected the relevant chatbot platform in combination with Google Cloud Dialogflow to structure the AI enabled chatbot, leveraging the combination to safeguard secure data integration, improve scalability, and deliver a unified real-time, customer experience.

We trained the AI enabled chatbot to understand user query intents and context using Natural Language Processing (NLP).

Once trained on over 250 different intents and 1250 utterances, the chatbot could manage a diverse range of queries.

Natural Language Processing enabled the AI enabled chatbot to obtain facts from queries and recall data from systems.

Integration with the client’s backend systems via APIs allowed the chatbot to retrieve and supply relevant data-rich responses with a very low failure rate.

In cases of complicated queries beyond the bot’s training, it smoothly transitioned the discussion to an individual human representative, ensuring a consistent client experience.

The AI-enabled chatbot was introduced to clients in a phased manner, and its success led to an extension to voice-based virtual assistants.

EmbArrk™ Workshop

Secure Data Integration

Voice-based Virtual Assistants

Outcomes

The AI chatbot was embedded within the client’s product dashboard, accessible to users only after validation to protect sensitive data.
Once authenticated, users can input industry-related queries.
The smart AI enabled solution identifies the user’s query intent and retrieves the correct answer from the client’s database.
Users can frame queries in numerous ways and still receive appropriate responses, thanks to the chatbot’s ability to understand various statements of the same query while maintaining context.
89% reduction in regular inbound customer queries.
95% increase in query resolution speed.
Over 1,000,000 queries are answered annually by the chatbot.
Thousands of human work hours saved annually.
Delivered data enriched query results from multiple systems

User Authentication

Faster Query Resolution

High Query Response Rate

More of Our Case Studies

See all case studies

The post Utilised an AI Chatbot to Decrease Customer Support Tickets by 89% appeared first on Arrk Group.

How Arrk’s AI Engineering Team Automated Data Harvesting, Reducing Costs by 48%…

Drashya Kuruwa — Fri, 20 Oct 2023 01:59:05 +0000

How Arrk’s AI Engineering Team Automated Data Harvesting, Reducing Costs by 48% and Speeding Up Time to Market - Resulting in Increased Revenue and Customer Satisfaction.

Our customer is a well-established global business intelligence organization specialising in the collection and improvement of massive datasets, which are subsequently published for customers to use in individual transactions and market analysis.

Customer

They are especially known for their research reports, market analysis, and consulting services, delivered to technology, IT, and business-related sectors. Their research and insights are often used by businesses to make informed decisions about technology investments and business strategies.

Their data harvesting and data entry operations are managed by a remote outsourced team, while a local call centre team is responsible for research and final publication. Our customer wanted to automate the data harvesting activity across several disparate data sets.

Problem Statement

The major problem faced by our client was the cost linked with remote outsourced data extraction and entry. The sheer volume of data involved in their operations required a manual data entry activity which resulted in significant expense. AI-enabled automation was identified as a possible solution; however, the complexity of this task was exacerbated by the complex nature of the source data. These sources, including various websites, presented data in different formats and standards, often including free-text fields, making the task of automating data extraction and entry a complex endeavour.

The final aim was to achieve a 50% automation rate, a goal that appeared ambitious at the outset but was deemed attainable.

Costly Offshore Data Entry

Complex Data Sources

Free-Text Fields

Automation Goal

Solution Development

Having conducted a rapid EmbArrk^TM discovery, using an iterative, product-oriented approach, a team of circa. 15 Arrkitects utilized Arrk’s agile@arrk project engineering methodology to deliver the project goals established during the EmbArrk^TM workshop. The journey towards automating data harvesting can be summarized in three key phases:

At the outset, the approach taken was a rule-based data-mapping activity. This method required customisations for each website to adapt to their unique terminologies, classifications, and free-text fields. Unfortunately, POC 1 didn’t yield results as expected due to the vast disparities in data presentation among different websites.

POC 2 introduced Natural Language Processing (NLP) and Named Entity Recognition (NER) techniques to extract key entities from the free-text fields. This approach demonstrated potential by pinpointing data locations, but it lacked the accuracy required to confidently detect and obtain accurate data. Efforts were made to combine NLP and NER with rule-based logic, but the complexity and cost of this approach became apparent.

In the final phase, a successful solution was created, blending rule-based processing and machine learning. The AI Engineering team precisely identified all the fields that the data entry team needed to populate, along with the associated validation rules. For each field, a decision was made to employ either rule-based processing or machine learning. The machine learning models, although time-consuming to build, provided the capability to generate data for fields that had previously necessitated human intervention.

Product-Oriented Approach

Agile Methodology

EmbArrk™ Workshop

Outcomes

This successful AI-enabled automation of data extraction and entry in our client’s research-based business stands as evidence of the power of combining rule-based processing and machine learning. By adapting to the unique challenges presented by diverse data sources, this project has not only substantially lowered costs but also increased accuracy, surpassing human capabilities in some instances. With the ongoing project and the introduction of generative AI, the client is ready to reap even greater benefits in the future, demonstrating the tremendous potential of AI-enabled solutions in data-intensive industries. The results of this project have been transformative:

Machine Learning Algorithms: The project now boasts five machine learning algorithms, with accuracies for AI-enabled data extraction and injection ranging between 95% to 98%. Remarkably, one of these algorithms outperformed human data entry accuracy.
Current Progress: While the project is still ongoing, it has already eliminated 41% of manual data extraction and entry. This equates to 500,000 data entries annually or 2,000 person-days of effort saved each year.
Future Prospects: The next phase of this AI Engineering project will involve the integration of generative AI alongside machine learning. This step is expected to exceed the original 50% automation target.

Improved Accuracy

Reduced Manual Data Entry

AI-Driven Solutions

Efficiency Gains

More of Our Case Studies

See all case studies

The post How Arrk’s AI Engineering Team Automated Data Harvesting, Reducing Costs by 48%… appeared first on Arrk Group.